Glare estimation method or system

Abstract

To provide a method and a system for rapidly estimating a glare.SOLUTION: A method that an information processor executes is a method for estimation including: acquisition processing of acquiring a position of the sun, an amount of direct solar radiation, an amount of diffused solar radiation, and a position of a radiation shielding device; and inputting the solar position, the amount of direct solar radiation, the amount of diffused solar radiation, and the position of a radiation shielding device into an estimation device for estimating the largest glare in a room and making the estimation device estimate an estimation value of the largest glare.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present invention relates to a glare estimation method or system. [Background Art]

[0002] As a conventional technique, a glare calculation method has been proposed (see, for example, Patent Document 1). [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Laid-Open No. 10-300568 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] However, in the above-mentioned technology, a large amount of labor and time is required to calculate glare, and it has been difficult to provide an estimation method or system that can perform estimation quickly. [Means for Solving the Problem]

[0005] In view of such problems, as one aspect, the present invention provides a method to be executed by an information processing apparatus, the method comprising: an acquisition process of acquiring a sun position, a direct solar radiation amount, a diffuse solar radiation amount, and a position of a solar shading device; and an estimation process of inputting the sun position, the direct solar radiation amount, the diffuse solar radiation amount, and the position into an estimator that estimates indoor maximum glare, and causing the estimator to estimate an estimated value of maximum glare; or a system that executes the estimation method. [Effects of the Invention]

[0006] With the above configuration, it is possible to provide a method or system capable of quickly estimating glare. [Brief Description of the Drawings]

[0007] [Figure 1]This is an overall configuration diagram of the information processing system according to this embodiment. [Figure 2] This figure shows the hardware configuration of the information processing device according to this embodiment. [Figure 3] This figure shows the functional configurations of (a) the distribution server and (b) the machine learning server according to this embodiment. [Figure 4] This diagram shows the structure of the learning device according to this embodiment. [Figure 5] This figure shows the training data according to this embodiment. [Figure 6] This flowchart shows the learning process according to this embodiment. [Figure 7] This figure shows an overview of the model according to this embodiment. [Figure 8] This figure shows the room that is the subject of the model according to this embodiment. [Figure 9] This is a flowchart of the estimation process according to this embodiment. [Modes for carrying out the invention]

[0008] The following matters will become clear from this specification and the accompanying drawings. The present invention will be described below with reference to the accompanying drawings, with reference to one embodiment thereof.

[0009] Figure 1 shows the configuration of an information processing system 1 according to one embodiment of the present invention. The information processing system 1 includes the computing units of a distribution server 10, a machine learning server 20, and one or more terminals 30. The distribution server 10, the machine learning server 20, and the terminals 30 are connected to each other via a communication network 5 so that they can send and receive data. The communication network 5 is a wireless or wired communication means, such as the Internet, WAN (Wide Area Network), LAN (Local Area Network), public communication network, or dedicated line. Although the information processing system 1 according to this embodiment is composed of the above-mentioned multiple information management devices, the present invention does not limit the number of these devices. Therefore, the information processing system 1 can be composed of one or more devices as long as they have the following functions.

[0010] Terminal 30 is a terminal operated by a user, or an information processing device that controls air conditioning equipment or shielding equipment.

[0011] The distribution server 10 is an information processing device that creates and stores data used for indoor solar radiation learning through various calculations, such as light environment simulations.

[0012] The machine learning server 20 has the function of performing machine learning to create a learning model, and the function of creating a process chart using the learning model.

[0013] Figure 2 shows an example of the hardware (hereinafter referred to as "information processing device 100") used to realize the distribution server 10, the machine learning server 20, and the terminal 30. As shown in the figure, the information processing device 100 includes a processor 101, a main memory 102, an auxiliary memory 103, an input device 104, an output device 105, and a communication device 106. These are connected to each other so as to be able to communicate via a communication means such as a bus (not shown).

[0014] Furthermore, it is not necessary that all configurations of the information processing apparatus 100 are implemented by hardware; all or part of the configurations may be implemented by virtual resources such as a cloud server in a cloud system, for example.

[0015] The processor 101 is configured using a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. When the processor 101 reads and executes a program stored in the main storage device 102, the functions of the distribution server 10, the machine learning server 20, and the terminal 30 are implemented.

[0016] The main storage device 102 is a device that stores programs and data, and is a ROM (Read Only Memory), a RAM (Random Access Memory), a non-volatile semiconductor memory (NVRAM (Non Volatile RAM)), or the like.

[0017] The auxiliary storage device 103 is, for example, various non-volatile memories (NVRAM: Non-volatile memory) such as an SSD (Solid State Drive) and an SD memory card, a hard disk drive, an optical storage device (CD (Compact Disc), DVD (Digital Versatile Disc), etc.), a storage area of a cloud server, or the like. Programs and data stored in the auxiliary storage device 103 are read into the main storage device 102 as needed.

[0018] The input device 104 is an interface that accepts input of information, and is, for example, a keyboard, a mouse, a touch panel, a card reader, a voice input device (microphone, etc.), a voice recognition device, or the like. The information processing apparatus 100 may be configured to accept input of information to and from another device via the communication device 106.

[0019] The output device 105 is an interface that outputs various types of information, and is, for example, a screen display device (liquid crystal monitor, LCD (Liquid Crystal Display), graphics card, etc.), a printing device or the like, an audio output device (speaker or the like), a speech synthesizer, or the like. The information processing apparatus 100 may be configured to output information to and from another apparatus via the communication apparatus 106.

[0020] The communication device 106 is a wired or wireless communication interface that implements communication between the information processing apparatus and other devices via the communication network 5, and is, for example, a NIC (Network Interface Card), a wireless communication module, a USB (Universal Serial Interface) module, a serial communication module, or the like.

[0021] [Functional Configuration of Distribution Server] FIG. 3(a) shows the main functions (software configuration) of the distribution server 10. As shown in the figure, the distribution server 10 includes the functions of a storage area 110 and a management unit 120. These functions are implemented by the processor 101 of the distribution server 10 reading and executing a program stored in the main storage device 102 or the auxiliary storage device 103 of the distribution server 10. In addition to the above functions, the distribution server 10 also includes functions such as an operating system, a file system, device drivers, and a DBMS (DataBase Management System).

[0022] Among the above functions, the storage area 110 is formed in the main storage device 102 or the auxiliary storage device 103 of the distribution server 10. The storage area 110 stores programs for executing simulation, simulation execution conditions, and simulation results. The storage area 110 stores these data as, for example, database tables, files managed by a file system, or the like.

[0023] The management unit 120 includes functions for setting simulation conditions, executing simulations, and saving simulation results.

[0024] [Machine learning server functional configuration] Figure 3(b) shows the main functions (software configuration) of the machine learning server 20. As shown in the figure, the machine learning server 20 includes a memory area 210 and a management unit 220. These functions are realized by the processor 101 of the machine learning server 20 reading and executing programs stored in the main memory 102 of the machine learning server 20. In addition to the above functions, the machine learning server 20 also includes functions such as an operating system, file system, device drivers, and DBMS (Database Management System).

[0025] The memory area 210 is formed in the main memory 102 or auxiliary memory 103 of the machine learning server 20. As shown in Figures 3(b) and 5, the memory area 210 stores training data 251 used for machine learning of the learner 221 (described later). The training data 251 has multiple combinations of solar position, direct solar radiation, diffuse solar radiation, solar shading device control position, and maximum glare, along with identifiers (IDs) attached to the combinations (Figure 5). Details on how the training data 251 is generated will be described later.

[0026] The management unit 220 has various functional configurations, such as blind control, which will be described later, but it includes at least a learner 221. The learner 221 learns the image features of an input image and has the function of outputting information that shows the estimation results of elements in the input image. Various types and structures of models can be used for a learner 221 with such functions, but in this embodiment, as shown in Figure 4, the learner 221 constructs a neural network such as a recurrent neural network or a convolutional neural network and performs deep learning.

[0027] The learner 221 has an input layer that accepts image input, an output layer that outputs the estimation results of the elements of interest, and a hidden layer that extracts features from the input image. Each of the input layer, output layer, and hidden layer has nodes (shown as white circles in the figure), and the nodes in each of these layers are connected by edges (shown as arrows in the figure). Note that the configuration of the learner 221 shown in Figure 4 is an example, and the number of nodes and edges, the number of hidden layers, etc. can be changed as appropriate.

[0028] [Learning process] The processes performed by the information processing system 1 with the above configuration will be explained below, mainly using the flowchart in Figure 6. In the processes performed by information processing system 1, training data is acquired by simulating the lighting environment of a certain room. In the following explanation, as an example, we will describe the case in which the lighting environment simulation is performed using Model 50 in Figure 7.

[0029] Model 50 is a model of a room 90 that has walls 91, a floor 92, windows 93, and blinds 94 positioned to cover the windows 93, as shown in Figure 8.

[0030] More specifically, Model 50 has a wall 51, a floor 52, a window 53, and a blind 54. The wall 51, floor 52, window 53, and blind 54 are models of the wall 91, floor 92, window 93, and blind 94 of Room 90, respectively. The blind 94 has its slat angle controlled by terminal 30. Depending on its slat angle, the blind 94 can adjust the degree of light blocking from a transmission position that completely transmits light to a shielding position that completely blocks light.

[0031] The floor surface 52 is defined by a grid cut at regular intervals and multiple grid points G corresponding to the intersections of the grid. The windows 53 correspond to the parts that transmit light, and the walls 51 are modeled as not transmitting light.

[0032] The blind 54 corresponds to the part that models the actual blind 94 and is positioned to cover the window 53. The blind 54 can adjust the proportion of light that enters from the window 53 and passes into the room according to its slat angle. In other words, the blind 54 can adjust the light shielding rate from a transmission position that completely transmits light to a shielding position that completely blocks light, according to its slat angle.

[0033] The processing performed in the information processing system 1 is realized by reading and executing programs stored in the main memory 102 or auxiliary memory 103 in each of the devices: the distribution server 10, the machine learning server 20, and the terminal 30. In the following processing, it may be explained that the processing of management units 120, 220, etc., generated by the program is executed by the distribution server 10 or the machine learning server 20.

[0034] In step S1, the control unit 120 sets the date and time, the position of the sun at that time, the amount of direct solar radiation, and the amount of diffuse solar radiation. The date and time are set at regular time intervals, such as every hour, between sunrise and sunset.

[0035] Direct and diffuse solar radiation may be obtained from historical meteorological data or may be artificially set.

[0036] In step S2, the control unit 120 sets the slat angle of the blind 54. The slat angle is set, for example, in increments of 1 degree between 0 degrees and 180 degrees.

[0037] Next, the control unit 120 simulates the lighting environment of Model 50 based on the sun position, direct solar radiation, diffuse solar radiation, and slat angle of the blind 54 set in steps S1 and S2, and calculates the glare inside the room.

[0038] More specifically, in glare calculations, the viewpoint P is set at a position corresponding to the height of a person's eyes from the floor surface 52 with respect to the grid point G (S3). That is, as shown in Figure 7, if the X, Y, and Z axes are defined, the coordinates of the grid point G are (Xp, Yp, 0), and the eye height is Zp, then the coordinates of the viewpoint P are expressed as (Xp, Yp, Zp).

[0039] The control unit 120 calculates the glare at viewpoint P in step S4 and repeats the same calculation for each grid (S5:NO).

[0040] Once the glare has been calculated for all grid points G and viewpoint P (S5:YES), the control unit 120 obtains the maximum glare, which is the largest of the acquired glare (S6).

[0041] The control unit 120 determines whether the acquisition of maximum glare has been completed for all slat angles that were scheduled in step S7. If it has not been completed (S7: NO), the control unit 120 returns to step S2 to set new slat angles and executes the processes from step S3 onwards.

[0042] If the acquisition of maximum glare has been completed for all of the planned slat angles (S7: YES), the control unit 120 determines whether the acquisition of maximum glare has been completed for all of the planned solar positions (which can also be understood as the planned date and time), direct solar radiation, and diffuse solar radiation (S8).

[0043] If the acquisition of maximum glare is not complete (S8:NO), the control unit 120 returns the process to step S1 and changes at least one of the solar position, direct solar radiation, and diffuse solar radiation. In this way, the control unit 120 repeats steps S1-S6 to acquire maximum glare for all of the scheduled solar position (date and time), direct solar radiation, and diffuse solar radiation.

[0044] Once the maximum glare has been acquired for all the planned solar positions, direct solar radiation, and diffuse solar radiation (S8:YES), the management unit 120 stores the relationship between the date and time, direct solar radiation, diffuse solar radiation, slat angle, and maximum glare in the storage area 110 and transmits it to the machine learning server 20. The machine learning server 20 stores the received data as training data 251 (S9).

[0045] The training data 251 created by the above process is used to train the learner 221, as described below. The learning of the learner 221 is carried out according to the flowchart in Figure 6.

[0046] In step S10, the management unit 220 of the machine learning server 20 sequentially learns combinations of date and time, direct solar radiation and diffuse solar radiation stored in the training data 251, the maximum glare, and the slat angle.

[0047] By performing this learning process, the learner 221 functions as a trained model (estimator) that estimates the maximum glare for the input date and time, direct solar radiation, diffuse solar radiation, and slat angle.

[0048] [Estimation process] Using the pre-trained learner 221, it becomes possible to estimate the maximum glare in a room R of an actual building. The details of the estimation process are explained below using the flowchart in Figure 9.

[0049] In step S21, the control unit 220 inputs the date and time, direct solar radiation, diffuse solar radiation, and the slat angle in room 90 into the learning device 221.

[0050] Based on the data input in step S21, the learning device 221 estimates and outputs the maximum glare in room 90 (S22).

[0051] The control unit 220 determines whether the estimated maximum glare is acceptable to the occupants of room 90 by comparing it to a threshold (S23).

[0052] If the maximum glare exceeds a threshold and is determined to be an unacceptable value (S23: NO), the control unit 220 changes the slat angle (S24) and returns the process to step S21. In this way, the control unit 220 causes the learner 221 to perform the estimation of the maximum glare again based on the changed slat angle, date and time, direct solar radiation, and diffuse solar radiation (S22).

[0053] If the estimated maximum glare is below a threshold, i.e., an acceptable value (S23: YES), the control unit 220 controls the slat angle of the blind 94 to match the slat angle input in step S21 (S25).

[0054] In this way, the control unit 220 controls the slat angle of the blinds 94 in room 90 so that the glare is within a comfortable range for the occupants. Alternatively, the control unit 220 instructs the control device or user that controls the slat angle of the blinds 94 in room 90 to change to an appropriate slat angle via the terminal 30.

[0055] <Variation> In this embodiment, a blind 94 was used, but other shading devices may be used. For example, a roller screen may be used as a shading device for the room 90 instead of the blind 94, and its opening and closing position may be controlled by the control unit 220.

[0056] In this case, in steps S1-S11, the relationship between the position of the roller screen, the date and time, direct solar radiation and diffuse solar radiation, and the maximum glare is obtained by simulation. These relationships are stored as training data 251 and used in the training process of the learner 221. In the estimation process, the control unit 220 can control the position of the roller screen in the room 90 according to the position estimated by the trained learner 221.

[0057] Thus, the present invention can be applied regardless of the type of shielding device.

[0058] <Effects> (Aspect 1) In the above embodiment, the information processing system 1 performs an estimation method which includes an acquisition process to acquire the position of the sun, the amount of direct solar radiation, the amount of diffuse solar radiation, and the position of the solar shading device, and an estimation process (S21-S25) in which the position of the sun, the amount of direct solar radiation, the amount of diffuse solar radiation, and the position of the blind 94 (corresponding to the solar shading device) are input to a learner 221 (corresponding to an estimator) that estimates the maximum glare in the room and causes it to estimate the value of the maximum glare.

[0059] With the above configuration, it is possible to quickly estimate the amount of glare generated indoors and appropriately estimate the measures to reduce glare.

[0060] (Aspect 2) In aspect 1, the information processing system 1 performs an estimation method which includes changing the position of the blinds 94 based on the estimated value to reduce the maximum glare in the room.

[0061] According to the above configuration, glare inside the room can be reduced, improving livability.

[0062] (Aspect 3) In aspect 1 or 2, the learner 221 is a trained model that has learned a dataset of the position of the sun, the amount of direct solar radiation, the amount of diffuse solar radiation, and the position of the solar shading device at a given time, and the maximum glare in the room.

[0063] In the above configuration, it is possible to estimate the maximum glare quickly and accurately by using a pre-trained model.

[0064] (Aspect 4) In any of aspects 1 to 3, the maximum glare learned by the trained model, the learner 221, is the maximum value among the glare measured at the height of a person's eye level at multiple points in the room.

[0065] In the above configuration, since the maximum glare is determined based on the human viewpoint, it is possible to calculate the maximum glare from the human viewpoint and estimate the appropriate slat angle.

[0066] (Aspect 5) In any of aspects 1 to 4, the maximum glare that the learner 221 learns is measured by a simulation using the indoor model 50.

[0067] In the above configuration, data on maximum glare is collected through simulation, allowing for the creation of a large amount of training data in a short period of time. [Explanation of Symbols]

[0068] Information Processing System 1 Server 10 Machine learning server 20 Terminal 30

Claims

1. A method for causing an information processing device to execute, An acquisition process to obtain the position of the sun, direct solar radiation, diffuse solar radiation, and the position of the solar shading device, The process includes an estimation process in which the solar position, the direct solar radiation, the diffuse solar radiation, and the position are input to an estimator, which is a trained model that has learned a dataset of the solar position, the direct solar radiation, the diffuse solar radiation, and the position of the solar shading device, and the maximum glare inside the room, in order to estimate the maximum glare. The aforementioned maximum glare represents the maximum value among the glare measured at multiple viewpoints set at the height of a human eye level at multiple locations within the room. Estimation method.

2. This process includes changing the position of the solar shading device based on the estimated value and reducing the maximum glare in the room. The estimation method according to claim 1.

3. The maximum glare learned by the aforementioned trained model is: Measured by simulation using the aforementioned indoor model, The estimation method according to claim 1.

4. A system comprising one or more information processing devices, which performs the estimation method described in any one of claims 1 to 3.

Images