Space control system, space control method, and program

Abstract

The space control system (1) includes a model calculation unit (406) that generates a reduced model of an object space (10) based on a result of fluid analysis of the object space (10) on which space control is performed, an assimilation unit (408) that performs assimilation processing using the reduced model generated by the model calculation unit (406) and environmental data obtained by sensing the object space (10) to thereby predict a spatial distribution of the object space (10), and an information processing unit (410) that searches for a control candidate for space control of the object space (10) based on the spatial distribution of the object space (10).

Description

Technical Field

[0001] This disclosure relates to space control systems, space control methods, and procedures. Background Technology

[0002] Previously, space control systems for predicting the spatial state within buildings equipped with air conditioning equipment were known. Patent Document 1 discloses a system that predicts the performance degradation of air conditioning equipment based on a performance trend database that links "partial load rate - cumulative operating time" with "partial load rate - COP (Coefficient of Performance) reduction rate," and generates an operating pattern where efficiency is optimal over a long period. The "partial load rate - cumulative operating time" refers to the cumulative operating time of the air conditioning equipment relative to the partial load rate of any pre-obtained period.

[0003] Existing technical documents Patent documents Patent Document 1: Japanese Patent Application Publication No. 2015-203544 Summary of the Invention

[0004] One aspect of the spatial control system disclosed herein includes: a model calculation unit that generates a scaled-down model of the object space based on the result of fluid analysis of the object space to be spatially controlled; an assimilation unit that performs assimilation processing using the scaled-down model generated by the model calculation unit and environmental data obtained by sensing the object space, thereby predicting the spatial distribution of the object space; and an information processing unit that searches for control candidates for spatial control of the object space based on the spatial distribution of the object space.

[0005] One aspect of the spatial control method disclosed herein includes: generating a scaled-down model of the object space based on the results of fluid analysis of the object space to be controlled; assimilating the scaled-down model and environmental data obtained by sensing the object space to predict the spatial distribution of the object space; and searching for control candidates for spatial control of the object space based on the spatial distribution of the object space.

[0006] One aspect of the program disclosed herein is a program for causing a computer to perform the aforementioned spatial control method.

[0007] Furthermore, the present disclosure in its entirety or in specific forms can be implemented by a system, method, integrated circuit, computer program or a recording medium such as a computer-readable CD-ROM, or by any combination of the system, method, integrated circuit, computer program and recording medium. Attached Figure Description

[0008] Figure 1 This is a block diagram illustrating the structure of the space control system in the implementation method.

[0009] Figure 2 This is a diagram representing an example of an object space that is subject to spatial control.

[0010] Figure 3 This diagram illustrates an example of the data set and input into the spatial state prediction device during fluid analysis.

[0011] Figure 4 It is a conceptual representation of the results of CFD analysis, the assimilated abbreviated model, and the graph controlling the abbreviated model.

[0012] Figure 5 This is a diagram illustrating an example of information related to the operating mode of a device.

[0013] Figure 6 This is a graph representing an example of actual data on partial load factor, COP, and power consumption.

[0014] Figure 7 This is another example of a graph showing actual performance data for partial load factor, COP, and power consumption.

[0015] Figure 8 This is a diagram illustrating an example of operating conditions derived through control optimization.

[0016] Figure 9 This is a diagram illustrating an example of operating conditions that can actually be operated by the equipment.

[0017] Figure 10 This is a diagram representing an example of a Pareto solution for controlling candidates.

[0018] Figure 11 This is a diagram representing an example of an object space within a building.

[0019] Figure 12 This is a flowchart illustrating the pre-implementation preparations for space control in the implementation method.

[0020] Figure 13 This is a flowchart illustrating the spatial control method of the implementation method. Detailed Implementation

[0021] In previous systems, the spatial state could only be predicted based on the candidate operating patterns of air conditioning equipment stored in the performance shift database, which resulted in a decrease in the prediction accuracy of the spatial state of the object space that became the object of spatial control.

[0022] This disclosure provides a spatial control system, etc., capable of suppressing the reduction in the prediction accuracy of the spatial state of an object space.

[0023] Hereinafter, embodiments will be described with reference to the accompanying drawings. The embodiments described below are either general or specific examples. The numerical values, shapes, materials, constituent elements, arrangement positions of constituent elements, connection methods, steps, and order of steps shown in the following embodiments are examples and are not intended to limit this disclosure. Furthermore, constituent elements not described in the independent claims in the following embodiments will be described as optional constituent elements.

[0024] Furthermore, these figures are schematic diagrams and not necessarily strictly representations. Additionally, identical reference numerals are used for substantially the same structures across different figures, and repetitive descriptions are sometimes omitted or simplified. Also, even when depicting the same object, the scale may be changed for convenience.

[0025] (Implementation Method) [Structure of Space Control System] The structure of the space control system in the embodiment will be described with reference to the accompanying drawings.

[0026] Figure 1 This is a block diagram illustrating the structure of the space control system 1 in the implementation method.

[0027] The space control system 1 is a system that predicts the state variables of the space within a building and searches for control candidates for controlling the space within the building based on the prediction.

[0028] The object of spatial control, namely the object space 10, is, for example, the space separated by walls in buildings such as residences, offices, shops, public facilities, entertainment facilities, art galleries, museums, factories, and warehouses. The state quantity of space is a physical quantity that represents the state of space, such as the temperature distribution, humidity distribution, wind speed (including wind direction) distribution, gas concentration distribution, and PM2.5 (fine particulate matter) distribution of space.

[0029] The space control system 1 includes a space state prediction device 400, one or more sensors 200, and one or more devices 300. The space state prediction device 400, sensors 200, and devices 300 can communicate via a network 100.

[0030] Figure 2 This is a diagram representing an example of the object space 10 that is subject to spatial control.

[0031] Sensor 200 is a device for detecting state quantities and boundary conditions at a specified location within the object space 10. State quantities at the specified location include, for example, temperature, humidity, wind speed, gas concentration, and PM2.5 levels. Boundary conditions at the specified location are physical quantities representing the external environment that affects the state quantities of the space, or the state of the boundary region between the space and the outside. External environments affecting the state quantities of the space include, for example, external air temperature, external wall temperature, external air humidity, external wind speed, external gas concentration, external PM2.5 levels, and solar radiation. The state of the boundary region between the space and the outside is, for example, the opening area (or opening angle) of a door or window installed in a building. Sensor 200 can be, for example, a thermometer, hygrometer, anemometer, gas concentration meter, PM2.5 meter, solar radiation meter, door sensor, or window sensor. Sensor 200 is installed within the object space 10 based on the optimization results of the measurement position optimization unit 411 described later.

[0032] The detection information (sensing information) detected by sensor 200 is sent to spatial state prediction device 400 via network 100.

[0033] Device 300 is a device that creates the environment of the target space 10, such as an air conditioning unit, ventilation fan, air purifier, circulator, or gas diffusion device. Device 300 is installed within the target space 10 of a building or at the boundary between the target space 10 and the outside. Furthermore, device 300 sends operating information, including current operating conditions and past operating history, to the space state prediction device 400. The operating conditions of device 300 include physical quantities such as the temperature, humidity, air volume, and air direction of the air supplied from device 300. If device 300 is an air conditioning unit, the operating information may include information related to the set air temperature, outgoing air volume, intake air volume, fan rotation speed, and power supply to the heat exchanger. If device 300 is a gas diffusion device that releases diffusing substances such as hypochlorous acid, antibacterial ions, or fragrances, the operating information may include information related to the concentration, release amount, and release direction of the released gas.

[0034] like Figure 1 As shown, the spatial state prediction device 400 includes a fluid calculation information acquisition unit 402, an indoor information acquisition unit 403, a control information acquisition unit 404, an information processing unit 410, a model calculation unit 406, an assimilation unit 408, and a storage unit 416. The information processing unit 410 includes a measurement location optimization unit 411, a partial load rate acquisition unit 412, and a COP acquisition unit 414. The fluid calculation information acquisition unit 402, the indoor information acquisition unit 403, and the control information acquisition unit 404 may also be included within the information processing unit 410.

[0035] The fluid computation information acquisition unit 402 acquires the simulation results of fluid analysis performed using the structural information of the object space 10 and the control capability information of the device 300. In this example, the fluid analysis is CFD (Computational Fluid Dynamics) analysis.

[0036] The structural information of the object space 10 includes information related to the shape, size, and configuration of the object space 10, as well as information related to the objects arranged within the object space 10, such as tables and partitions, and their positions. Information related to the shape of the object space 10 is, for example, data obtained by transforming the object space 10 into a point group using the finite volume method after 3D modeling. The structural information of the object space 10 is pre-input into the fluid calculation information acquisition unit 402 by users of the object space 10. Furthermore, the structural information of the object space 10 can also be obtained by photographing the object space 10 using a camera installed on the device 300.

[0037] The control capability information of device 300 refers to information indicating the spatial control capability of device 300. For example, if device 300 is an air conditioning unit, the control capability information of device 300 includes information such as air volume, air direction, and outlet temperature. The control capability information of device 300 is pre-input into the fluid calculation information acquisition unit 402 by users or others using the object space 10.

[0038] Figure 3 This diagram illustrates an example of the data set and input into the spatial state prediction device 400 during fluid analysis.

[0039] exist Figure 3 The document shows information related to the model settings used for fluid analysis, specifically information related to turbulence models and steady / unsteady flow. Additionally, in... Figure 3 The diagram illustrates, as an example, the structural information of object space 10, including information related to the computational region / mesh size, wall boundary conditions, and thermal boundary conditions. Additionally, in... Figure 3 The figure shows flow boundary data as an example of control capability information for device 300. In this figure, as flow boundary data, information related to the air volume of the exhaust port of the two air conditioners A1 and A2, the intake volume and intake temperature of the intake port, the blowing temperature, air volume and air direction of each air conditioner A1 and A2, and the surface pressure and inflow temperature at two points in the gap (slit) of the object space 10 are shown.

[0040] The spatial state prediction device 400 performs fluid analysis based on the structural information of the object space 10 and the control capability information of the device 300, and outputs the simulation results of the fluid analysis.

[0041] The model calculation unit 406 generates a reduced model of the object space 10 based on the results of fluid analysis of the object space 10. For example, the model calculation unit 406 generates the reduced model using intrinsic orthogonal decomposition (POD) based on the simulation results of fluid analysis obtained by the fluid calculation information acquisition unit 402. Intrinsic orthogonal decomposition refers to a decomposition method that extracts low-dimensional components from the provided multidimensional data.

[0042] Figure 4 It is a conceptual representation of the results of CFD analysis, the assimilated abbreviated model, and the graph controlling the abbreviated model.

[0043] The generation sequence of the abbreviated model is explained. First, the physical quantities (or state variables) of object space 10 obtained through CFD analysis are transformed into one-dimensional information arranged in grid point order, and a matrix with the number of data points is created. Then, the average difference of the generated matrix is ​​transformed into a square matrix, and the pattern composed of intrinsic values / intrinsic vectors is obtained. The obtained pattern is assigned POD coefficients, thereby reconstructing the fluid field of object space 10.

[0044] In this example, according to Figure 4 The CFD analysis results of the 100 cases shown in (a) are generated. Figure 4 (b) shows the abbreviated models of the 10 patterns.

[0045] In reality, as operating conditions, the air conditioner has 5 levels of outlet temperature, 2 levels of airflow, and 2 levels of exhaust angle. There are also cases where the air conditioner is turned off. These combinations of levels exist for both air conditioners. Furthermore, as boundary conditions, the wall and gap air temperatures have 2 levels. When executing all combinations of cases, (5×2×2+1) 2 ×2=882, performing analysis on 882 cases, the computation time for predicting spatial states increases. Therefore, 100 cases are extracted from the 882 cases at arbitrary intervals, and the analysis of the other 782 cases, which exist between the 100 cases, is replaced with a simplified model of 10 patterns.

[0046] A shortened model is a model that can maintain the essential behavior of spatial control in object space 10 while reducing the dimensionality of the model. By using a shortened model, the parsing time and data volume of spatial control can be reduced.

[0047] The assimilation unit 408 uses the abbreviated model generated by the model calculation unit 406 and the environmental data obtained by sensing the object space 10 to perform assimilation processing, thereby predicting the spatial distribution of the object space 10. For example, the assimilation unit 408 uses the abbreviated model generated by the model calculation unit 406 and the environmental data of the object space 10 obtained by the indoor information acquisition unit 403 to determine appropriate initial values, boundary values, and parameters, so that the phenomena occurring in the spatial distribution of the object space 10 can be reproduced. Thus, the assimilation unit 408 generates the assimilated abbreviated model.

[0048] In order to accurately predict the spatial distribution based on assimilation processing, the measurement location optimization unit 411 searches for the optimal location of the sensors 200. However, the locations where the sensors 200 can be placed within the object space 10 are constrained by places that do not obstruct human movement and places without furniture. Therefore, using a simplified model generated by the model calculation unit 406, the sensor sensitivity of the sensors 200 is quantified under each coordinate, the spatial state is understood, and a trade-off relationship related to the number of sensors 200 and the placement locations of the sensors 200 is obtained. Thus, the number of sensors 200 and the placement locations of the sensors 200 in the object space 10 are optimized. As an example of the optimization algorithm used, NSGA-2 (Elitist Non-dominated Sorting Genetic Algorithm) is a multi-objective genetic algorithm.

[0049] The assimilation unit 408 obtains the environmental data by changing the position of the sensor 200 located in the object space 10, and performs assimilation processing using the environmental data before and after the change of the sensor 200's position, thereby predicting the spatial distribution before and after the change. The information processing unit 410 determines the appropriate position of the sensor 200 based on the spatial distribution before and after the change.

[0050] The control information acquisition unit 404 acquires the control conditions of each simulation result acquired by the fluid calculation information acquisition unit 402.

[0051] Information processing unit 410 uses the assimilated abbreviated model and control conditions obtained from the simulation results by control information acquisition unit 404 to perform machine learning, thereby generating a control abbreviated model (see reference). Figure 4 (c). The control abbreviated model is a model that predicts the spatial state by taking control conditions as input values. The information processing unit 410 learns the POD coefficients of the physical quantities (state quantities) of the object space 10 in the abbreviated model and the control conditions of the simulation results through Gaussian process distribution, thereby generating a predictive model of POD coefficients with control conditions as input. Hereinafter, the control abbreviated model is sometimes referred to as the learned abbreviated model.

[0052] In this way, the information processing unit 410 learns the assimilated abbreviated model using the control conditions in fluid analysis as input values, thereby generating a learned abbreviated model. Furthermore, the information processing unit 410 predicts the spatial distribution of the object space 10 by assimilating the learned abbreviated model and environmental data, and searches for control candidates for spatial control of the object space 10 based on this spatial distribution. Searching for control candidates refers to extracting operating patterns from various operating patterns for appropriate spatial control. The information processing unit 410 searches for control candidates to make the object space 10 approximate the target spatial distribution.

[0053] The learned abbreviated model is stored in storage unit 416. Additionally, storage unit 416 stores information related to physical quantities (state quantities) such as temperature desired by the user, as well as spatial control (air quality control, etc.). Storage unit 416 may also store information related to the environmental state and spatial distribution of the target space 10.

[0054] The following describes an example of how the information processing unit 410 obtains information related to the partial load rate, power consumption, and COP of the device 300, and searches for control candidates based on this information.

[0055] The indoor information acquisition unit 403 acquires environmental data of the object space 10 from the sensor 200, whose position is determined by the measurement position optimization unit 411. In addition, the indoor information acquisition unit 403 acquires the operating mode of the equipment 300 that performs space control (air quality control, etc.) of the object space 10.

[0056] Figure 5 This is a diagram illustrating an example of information related to the operating mode of device 300.

[0057] exist Figure 5 The settings temperature and set air volume of air conditioners A1 and A2 are displayed in chronological order.

[0058] The indoor information acquisition unit 403 acquires information related to the power consumption of the device 300 based on the operating mode of the device 300.

[0059] Power consumption is calculated using the following formula (Equation 1).

[0060] Power consumption = W fan +W const …(Formula 1) W fan The heat required for the fan to rotate, W const The amount of heat needed to maintain the room temperature In addition, W fanThe relationship between the set airflow and the measured current value under air supply conditions is derived. The intake and exhaust temperatures are constant under steady-state conditions, therefore W... const The calculation is performed using Equation 2 as shown below.

[0061] W const =J(T) out -T inlet ... (Equation 2) T out The air conditioner's blowout temperature, T inlet Air conditioner intake temperature J, for example, can be compared with the measured current value every 1 second (T) out -T inlet The regression equation is used to calculate the result.

[0062] Information related to power consumption is output to the information processing unit 410.

[0063] The partial load rate acquisition unit 412 acquires the partial load rate of equipment 300. The partial load rate of equipment 300 is calculated using the following formula (3).

[0064] Partial load rate = (output of air conditioning equipment) / (rated output of air conditioning equipment) ... (Equation 3) The output of the air conditioning equipment is calculated based on the intake air volume and the intake-exhaust enthalpy difference. For example, the partial load rate acquisition unit 412 obtains the intake-exhaust enthalpy from the spatial distribution predicted by the assimilation unit 408, and calculates the output of the air conditioning equipment in the current spatial distribution.

[0065] The heat output of the air conditioning equipment is calculated using the following formula (Equation 4).

[0066] Heat = (Specific heat of air × Air density × Intake air volume [CMH] × Intake-out enthalpy difference [kJ / kg]) / 3600 [(kJ / h) / kW] … (Equation 4) The COP (Coefficient of Performance) of the device 300 is derived by the COP acquisition unit 414. COP is a coefficient used to check the energy consumption efficiency of refrigeration and heating appliances, which is called the coefficient of performance (operation coefficient). COP is calculated using the following formula (5).

[0067] COP = (Output of air conditioning equipment) / (Power consumption of air conditioning equipment) ... (Equation 5) The storage unit 416 stores information related to power consumption obtained from the indoor information acquisition unit 403, the partial load rate obtained from the partial load rate acquisition unit 412, and the COP obtained from the COP acquisition unit 414.

[0068] Furthermore, calculations related to power consumption, part load rate, and COP do not necessarily need to be performed internally by the space condition prediction device 400; they can also be performed by an external computer. The indoor information acquisition unit 403 can also acquire information related to the power consumption calculation results from an external computer. The part load rate acquisition unit 412 can also acquire information related to the part load rate calculation results from an external computer. The COP acquisition unit 414 can also acquire information related to the COP calculation results from an external computer.

[0069] The information processing unit 410 acquires information related to the partial load rate, power consumption, and COP (Coefficient of Performance) of the equipment 300 used for space control, and searches for control candidates using at least one of power consumption and COP as evaluation indicators. Low power consumption and high COP are preferred.

[0070] Figure 6 This is a graph representing an example of actual data on partial load factor, COP, and power consumption. Figure 7 This is another example of a graph showing actual performance data for partial load factor, COP, and power consumption.

[0071] exist Figure 6 The data shown is the actual performance data for air conditioner A1. Figure 7 The actual performance data for air conditioner A2 is shown in the figure. Figure 6 and Figure 7 The horizontal axis represents the partial load factor, the vertical axis to the left represents the Coefficient of Performance (COP), and the vertical axis to the right represents power consumption. Furthermore, the scale of the right vertical axis is set such that the scale of the actual power consumption data is approximately smaller than the scale of the actual COP data.

[0072] like Figure 6 and Figure 7 As shown, a higher partial load rate results in a higher COP, but the COP decreases when the partial load rate is too high. Furthermore, power consumption remains relatively stable within a specified range after the partial load rate increases slightly, but if the partial load rate becomes excessively high, power consumption increases accordingly.

[0073] Information Processing Unit 410 based on Figure 6 and Figure 7 The actual performance data shown is used to search for control candidates. For example, the information processing unit 410 sets the part load rate at which the difference between COP and power consumption is maximized as the optimal part load rate (see reference). Figure 6 and Figure 7 The operating style used to achieve this load rate is set as the control candidate.

[0074] In addition, the information processing unit 410 can also derive the power consumption when the COP is at its maximum. If the power consumption is within an acceptable range, the partial load rate corresponding to the maximum COP is set as the optimal partial load rate, and the operating mode used to achieve this partial load rate is used as a control candidate.

[0075] In this way, the information processing unit 410 derives the partial load rate when the difference between power consumption and COP is at its maximum, and searches for control candidates that can maintain this partial load rate.

[0076] In addition, the information processing unit 410 can also derive the partial load rate when the difference between power consumption and COP is above a predetermined threshold and the change in the difference between power consumption and COP relative to the change in partial load rate is within a predetermined range, and search for control candidates that can maintain that partial load rate.

[0077] Furthermore, when searching for control candidates, the information processing unit 410 uses a multi-objective genetic algorithm to reconstruct the space based on the predicted POD coefficients, thereby obtaining the spatial distribution and optimizing the control conditions for the operation of the device 300.

[0078] Figure 8 This is a diagram illustrating an example of operating conditions derived through control optimization. Figure 9 This is a diagram illustrating an example of the operating conditions under which the equipment 300 can actually be operated.

[0079] The operating conditions obtained through control optimization are selected from continuous values. In contrast, the actual operable operating conditions are predetermined based on the specifications of equipment 300. Therefore, it is necessary to convert the operating conditions derived through control optimization into actual operable operating conditions to form an operating pattern. Figure 9 The control conditions 1 and 2 shown are obtained by changing the operating conditions derived through control optimization into actual operable operating conditions.

[0080] Figure 10 This is a diagram representing an example of a Pareto solution for controlling candidates.

[0081] Figure 10 The horizontal axis represents comfort, and the vertical axis represents power consumption. Comfort, for example, is the proportion of the total runtime during which the desired spatial distribution can be achieved.

[0082] Control condition 1 represents the comfort and power consumption results when two air conditioners are running, while control condition 2 represents the comfort and power consumption results when one air conditioner is running. In this diagram, through control optimization, two control conditions with equal comfort levels but significantly different power consumption are extracted. The information processing unit 410 lists these two control conditions as control candidates and outputs them.

[0083] For example, the space control system 1 can also display the listed multiple control candidates on a user's information terminal (e.g., a smartphone or tablet). Additionally, the space control system 1 can also use the highest-priority control candidate among the listed multiple control candidates to control the operation of the device 300.

[0084] The space control system 1 of this embodiment includes: a model calculation unit 406, which generates a scaled-down model of the object space 10 based on the fluid analysis results of the object space 10 to be controlled; an assimilation unit 408, which performs assimilation processing using the scaled-down model generated by the model calculation unit 406 and environmental data obtained by sensing the object space 10, thereby predicting the spatial distribution of the object space 10; and an information processing unit 410, which searches for control candidates when performing spatial control on the object space 10 based on the spatial distribution of the object space 10.

[0085] In this way, a simplified model of object space 10 is generated. Using this simplified model and environmental data for assimilation, the spatial distribution of object space 10 is predicted, thereby suppressing the decrease in prediction accuracy of the spatial state of object space 10. Furthermore, by searching for control candidates for spatial control of object space 10 based on the aforementioned spatial distribution, the search for control candidates can be appropriately performed.

[0086] [Spatial Control Methods] The spatial control method described in the implementation plan is explained.

[0087] Figure 11 This is a diagram representing an example of object space 10 within a building.

[0088] exist Figure 11 The diagram shows an observation of object space 10 from above. Figure 11 In this device, a sensor 200 is used to detect state quantities within the object space 10, and a thermometer, a hygrometer, and an anemometer are provided in the object space 10. In addition, an air conditioner A1, an air conditioner A2, and multiple ventilation fans are provided in the object space 10 as a device 300 to create the environment of the object space 10.

[0089] The structural information of the object space 10 includes, for example, room layout information and information related to the location / shape of everyday utensils. The control capability information of the equipment 300 includes, for example, the operating information of the air conditioning equipment (air conditioners A1 and A2), such as airflow, airflow direction, and outlet temperature. The space state prediction device 400 uses this information to perform fluid analysis simulations.

[0090] Figure 12 This is a flowchart illustrating the pre-implementation preparations for space control in the implementation method.

[0091] exist Figure 12The diagram illustrates the steps required as preparation before implementing space control. The simulation is conducted under multiple control conditions.

[0092] First, the spatial state prediction device 400 sets the control range of the control factors (step S100). For example, the spatial state prediction device 400 uses the operating limits of the device 300 as the control range and sets arbitrary numerical intervals as calculation conditions. Arbitrary numerical intervals are set because performing simulations under all control modes would result in a huge computational load.

[0093] Therefore, the spatial state prediction device 400 determines the control pattern to be calculated (step S102). For example, the spatial state prediction device 400 uses a Latin superlattice for random sampling to determine the control pattern to be calculated.

[0094] The spatial state prediction device 400 performs a simulation in the control style determined in step S102 and obtains the calculation results (step S104).

[0095] The spatial state prediction device 400 generates a simplified model using intrinsic orthogonal decomposition based on the physical quantities under each operating condition obtained from the calculation results in step S104 (step S106).

[0096] In addition, the spatial state prediction device 400 optimizes the positions of the sensors 200 in the object space 10 (step S108). For example, based on the simplified model generated in step S106, the spatial state prediction device 400 quantifies the sensor sensitivity when the sensors 200 are set at various coordinates in the object space 10, obtains a trade-off between the number of sensors and the understanding of the airflow state, and thereby determines the number and position of the sensors 200. Furthermore, if the sensor sensitivity is already sufficient, step S108 can be omitted.

[0097] The spatial state prediction device 400 performs data assimilation processing during trial operation to predict the spatial state of the object space 10 (step S110). For example, in order to obtain the optimal partial load rate, the spatial state prediction device 400 conducts trial operation under different control conditions and different external temperatures, obtaining information related to the state quantities of the object space 10 from the sensor 200 whose position was determined in step S108. The state quantities are at least one of temperature, humidity, air volume, and wind direction. The spatial state prediction device 400 uses the state quantities obtained in step S110 and the abbreviated model generated in step S106 to perform data assimilation processing and predict the spatial state under each control condition.

[0098] Next, the spatial state prediction device 400 generates a control abbreviated model (step S112). For example, the spatial state prediction device 400 uses the abbreviated model generated in step S106 and the control conditions in the calculation results obtained in step S104 to generate a prediction model, i.e., a control abbreviated model, with the control conditions as input values ​​for the POD coefficients. The control abbreviated model is an example of a learned abbreviated model.

[0099] Additionally, the spatial state prediction device 400 sets constraints on the part load rate (step S114). For example, the spatial state prediction device 400 uses the predicted spatial distribution under each control condition to plot the actual data of the part load rate and COP of the device 300, and the actual data of the part load rate and power consumption of the device 300, and extracts the optimal part load rate. The derived optimal part load rate is used as a constraint when searching for control candidates. Furthermore, step S114 can also be executed simultaneously with step S112.

[0100] Figure 13 This is a flowchart illustrating the spatial control method implemented in this embodiment.

[0101] Figure 13 The steps performed by the space control system 1 are shown.

[0102] The space control system 1 acquires the control information of the current device 300 in the object space 10 (step S200). In the control information, besides... Figure 5 In addition to the control conditions shown, it also includes time series data such as the running time of each control mode.

[0103] The space control system 1 acquires the state variables of the object space 10 (step S202). Specifically, the space control system 1 obtains the state variables from the object space 10. Figure 12 In step S108, the sensor 200, whose position is determined, obtains environmental data via network 100.

[0104] The space control system 1 predicts the spatial state of the object space 10 (step S204). For example, the space control system 1 uses the control information obtained in step S200 as input values ​​and applies them to... Figure 12 The control abbreviated model generated in step S112 is used to predict the spatial distribution.

[0105] In addition, the space control system 1 uses the predicted spatial distribution to obtain the partial load factor and COP of the device 300 (step S206). Furthermore, the space control system 1 obtains the power consumption of the device 300.

[0106] The space control system 1 searches for control candidates based on the partial load rate, COP and power consumption obtained in step S206 (step S208).

[0107] The space control system 1 outputs information related to the extracted control candidate (step S210). For example, the space control system 1 may also use the optimal partial load rate operating mode as a control candidate and display it on the user's information terminal. For example, the space control system 1 may also control the operation of the equipment 300 using the optimal partial load rate operating mode.

[0108] By performing the steps described above, it is possible to search for control candidates that balance comfort and energy efficiency.

[0109] (Summarize) An example of a space control system, etc., according to one aspect of this disclosure is provided.

[0110] Example 1's space control system 1 includes: a model calculation unit 406 that generates a scaled-down model of the object space 10 based on the fluid analysis results of the object space 10 to be controlled; an assimilation unit 408 that performs assimilation processing using the scaled-down model generated by the model calculation unit 406 and environmental data obtained by sensing the object space 10, thereby predicting the spatial distribution of the object space 10; and an information processing unit 410 that searches for control candidates when performing spatial control on the object space 10 based on the spatial distribution of the object space 10.

[0111] In this way, by using a scaled-down model of object space 10 and environmental data for assimilation processing, the spatial distribution of object space 10 can be predicted, thereby suppressing the reduction in the prediction accuracy of the spatial state of object space 10. In addition, by searching for control candidates for spatial control of object space 10 based on the aforementioned spatial distribution of object space 10, the search for control candidates can be performed appropriately.

[0112] The space control system 1 in Example 2 can also be the same as the space control system described in Example 1, where the information processing unit 410 takes the control conditions in the fluid analysis as input values, learns the assimilated abbreviated model, generates the learned abbreviated model, and predicts the spatial distribution of the object space 10 by using the learned abbreviated model and environmental data for assimilation processing, and searches for control candidates based on the spatial distribution.

[0113] In this way, by using the learned abbreviated model and environmental data for assimilation, the spatial distribution of object space 10 can be predicted, thereby suppressing the reduction in the prediction accuracy of the spatial state of object space 10.

[0114] The space control system 1 in Example 3 can also be, in the space control system described in Example 1, where the information processing unit 410 searches for control candidates in a way that makes the object space 10 approach the spatial distribution as the target.

[0115] In this way, by searching for control candidates in a manner that approximates the spatial distribution of the target, the search for control candidates can be carried out appropriately.

[0116] The space control system 1 in Example 4 can also be, in any of the space control systems in Examples 1 to 3, where the assimilation unit 408 changes the position of the sensor 200 installed in the object space 10 to obtain environmental data, and uses the environmental data before and after the change of the position of the sensor 200 to perform assimilation processing, thereby predicting the spatial distribution before and after the change, and the information processing unit 410 determines the position of the sensor 200 based on the spatial distribution before and after the change.

[0117] Therefore, the sensor 200 can be positioned appropriately within the object space 10. This helps to suppress the reduction in the prediction accuracy of the spatial state of the object space 10.

[0118] The space control system 1 in Example 5 can also be, in the space control system described in Example 2, where the information processing unit 410 obtains information related to the partial load rate, power consumption, and COP of the device 300 that performs space control, and uses at least one of power consumption and COP as an evaluation index to search for control candidates.

[0119] In this way, by using at least one of power consumption and COP as evaluation indicators to search for control candidates, the search for control candidates can be performed appropriately.

[0120] The space control system 1 in Example 6 can also be, in the space control system described in Example 5, where the information processing unit 410 derives the partial load rate when the difference between power consumption and COP is at its maximum, and searches for control candidates that can maintain that partial load rate.

[0121] Thus, for example, information related to the optimal partial load rate can be obtained, allowing for the appropriate search of control candidates.

[0122] The space control system 1 in Example 7 can also be, in the space control system described in Example 5, where the information processing unit 410 outputs the partial load rate when the difference between power consumption and COP is above a predetermined threshold and the change in the difference between power consumption and COP relative to the change in partial load rate is within a predetermined range, and searches for control candidates that can maintain that partial load rate.

[0123] This allows us to obtain information related to the part load factor with strong anti-interference capabilities and to appropriately search for control candidates.

[0124] Example 8's spatial control method includes: generating a scaled-down model of the object space 10 based on the fluid analysis results of the object space 10 to be spatially controlled; assimilating the scaled-down model and environmental data obtained by sensing the object space 10 to predict the spatial distribution of the object space 10; and searching for control candidates for spatial control of the object space 10 based on the spatial distribution of the object space 10.

[0125] In this way, by using a scaled-down model of object space 10 and environmental data for assimilation processing, the spatial distribution of object space 10 can be predicted, thereby suppressing the reduction in the prediction accuracy of the spatial state of object space 10. In addition, by searching for control candidates for spatial control of object space 10 based on the aforementioned spatial distribution of object space 10, the search for control candidates can be performed appropriately.

[0126] The program in Example 9 is a program used to make the computer execute the space control method described in Example 8.

[0127] Therefore, a spatial control method can be implemented that can suppress the reduction in prediction accuracy of the spatial state of object space 10.

[0128] (Other implementation methods) The space control system and other embodiments of this disclosure have been described above based on the embodiments, but this disclosure is not limited to these embodiments. Various modifications to the embodiments that can be conceived by those skilled in the art, as well as other ways of constructing by combining some of the constituent elements of the embodiments, are also included within the scope of this disclosure, as long as they do not depart from the spirit of this disclosure.

[0129] The above description illustrates an example of the spatial state prediction device 400 being connected to the device 300 via a communication network, but is not limited to this. For example, the spatial state prediction device 400 may also be located inside the device 300. In this case, the sensor 200 may also be located inside the device 300 and connected to the spatial state prediction device 400.

[0130] The spatial state prediction device described above, as a hardware structure, is implemented using a non-volatile memory storing a program, a volatile memory serving as a temporary storage area for executing the program, input / output ports, a communication interface, and a processor for executing the program. Each component of the spatial state prediction device is implemented by a processor that executes the program stored in the memory. The spatial state prediction device can be implemented using portable terminals such as fixed PCs (Personal Computers), smartphones, and tablets, dedicated computers, servers (e.g., cloud servers), or combinations thereof.

[0131] Alternatively, each component can be constructed using dedicated hardware, or implemented by executing software programs suitable for each component. Each component can also be implemented by a program execution unit such as a CPU or processor reading and executing software programs recorded on a recording medium such as a hard disk or semiconductor memory.

[0132] Furthermore, the order of the steps in the execution flowchart is illustrative for the purpose of explaining this disclosure, and may be in a different order than described above. Additionally, some of the steps described above may be executed simultaneously (in parallel) with other steps, or some of the steps may not be executed at all.

[0133] Furthermore, the segmentation of functional blocks in the block diagram is one example. Multiple functional blocks can also be implemented as a single functional block, or a single functional block can be divided into multiple functional blocks, or some functionality can be transferred to other functional blocks. Additionally, the functionality of multiple functional blocks with similar functions can be processed in parallel or time-sharing by a single piece of hardware or software.

[0134] Furthermore, the spatial state prediction device described above can be implemented as a single device or as multiple devices. When the spatial state prediction device is implemented by multiple devices, the constituent elements of the spatial state prediction device can be arbitrarily distributed among the multiple devices. When the spatial state prediction device is implemented by multiple devices, the communication method between these multiple devices is not particularly limited; it can be wireless communication or wired communication. Alternatively, wireless communication and wired communication can be combined between the devices.

[0135] Furthermore, the constituent elements described in the above embodiments can be implemented as software, typically as integrated circuits, i.e., LSIs. They can be formed as a single chip, or as a chip including some or all of them. Here, they are referred to as LSIs, but depending on the level of integration, they are sometimes also called ICs, system LSIs, super LSIs, or extra-large LSIs. In addition, the method of integrated circuitization is not limited to LSIs; it can also be implemented through dedicated circuits (general-purpose circuits that execute dedicated programs) or general-purpose processors. LSIs can also utilize FPGAs (Field-Programmable Gate Arrays) that can be programmed after manufacturing, or reconfigurable processors that can reconfigure the connections or settings of the circuit units inside the LSI. Furthermore, if integrated circuitization technologies that replace LSIs emerge with advancements in semiconductor technology or other derived technologies, these technologies can of course be used for the integration of constituent elements.

[0136] A system LSI is a multifunctional LSI that integrates multiple processing units onto a single chip. Specifically, it is a computer system comprising a microprocessor, ROM (Read Only Memory), RAM (Random Access Memory), etc. The computer program is stored in the ROM. The system LSI performs its functions by having the microprocessor execute the computer program.

[0137] Alternatively, this disclosure may also be a computer program that enables a computer to perform the characteristic steps included in the method of using the battery pack.

[0138] Alternatively, for example, the program can also be a program for causing a computer to execute. Another aspect of this disclosure can be a computer-readable, non-transitory recording medium on which such a program is recorded. For example, such a program can be recorded on a recording medium and distributed or circulated. For example, by installing the distributed program on a device having another processor and causing that processor to execute the program, the device can perform the aforementioned processes.

[0139] According to the spatial control system disclosed herein, the reduction in prediction accuracy of spatial control of the object space can be suppressed.

[0140] Industrial applicability This disclosure can be applied to spatial control systems that can suppress the reduction in predictive accuracy of spatial control in the object space.

[0141] Explanation of reference numerals in the attached figures 1. Space Control System 10 Object Space 100 Network 200 sensors 300 devices 400 Spatial State Prediction Device 402 Fluid Computing Information Acquisition Department 403 Indoor Information Acquisition Department 404 Control Information Acquisition Department 406 Model Computation Department 408 Assimilation Department 410 Information Processing Department 411 Measurement Position Optimization Department 412 Partial Load Factor Acquisition 414 COP Acquisition Department 416 Storage Department

Claims

1. A space control system, wherein, have: The model computation unit generates a simplified model of the object space based on the fluid analysis results of the object space, which is the object being controlled in space. The assimilation unit performs assimilation processing using the abbreviated model generated by the model calculation unit and the environmental data obtained by sensing the object space, thereby predicting the spatial distribution of the object space; as well as The information processing unit searches for control candidates for spatial control of the object space based on the spatial distribution of the object space.

2. The space control system according to claim 1, wherein, The information processing unit takes the control conditions in the fluid analysis as input values, learns the assimilated abbreviated model, thereby generating a learned abbreviated model, and predicts the spatial distribution of the object space by using the learned abbreviated model and the environmental data for assimilation processing, and searches for control candidates based on the spatial distribution.

3. The space control system according to claim 1, wherein, The information processing unit searches for control candidates in a manner that makes the object space approximate the spatial distribution of the target.

4. The space control system according to claim 1, wherein, The assimilation unit changes the position of the sensor located in the object space to obtain the environmental data, and uses the environmental data before and after the change of the sensor position to perform the assimilation process, thereby predicting the spatial distribution before and after the change. The information processing unit determines the position of the sensor based on the spatial distribution before and after the change.

5. The space control system according to claim 2, wherein, The information processing unit obtains information related to the partial load rate, power consumption, and coefficient of performance (COP) of the device performing the space control, and uses at least one of the power consumption and the COP as evaluation indicators to search for control candidates.

6. The space control system according to claim 5, wherein, The information processing unit derives the partial load rate when the difference between the power consumption and the COP is maximized, and searches for control candidates that can maintain this partial load rate.

7. The space control system according to claim 5, wherein, The information processing unit outputs the partial load rate when the difference between the power consumption and the COP is above a predetermined threshold and the change in the difference between the power consumption and the COP relative to the change in the partial load rate is within a predetermined range, and searches for control candidates that can maintain the partial load rate.

8. A space control method, wherein, include: The step of generating a scaled-down model of the object space based on the fluid analysis results of the object space being controlled. The step of assimilating the simplified model and environmental data obtained by sensing the object space to predict the spatial distribution of the object space; as well as Based on the spatial distribution of the object space, search for candidate control steps when performing spatial control on the object space.

9. A program for causing a computer to perform the space control method of claim 8.

Images