Warming index estimation system

Abstract

A thermal index estimation system is provided with: a housing that defines an internal space and is provided with a vent hole that communicates the internal space with an external space of the housing; a temperature measuring unit which is disposed inside the housing and measures the temperature of the internal space; a detection unit that detects movement information indicating movement of the housing; a light amount measurement unit that measures the amount of light received by the housing; and an estimation unit that estimates a warm index in the external space on the basis of the temperature of the internal space, the motion information, and the light amount.

Description

Technical Field

[0001] The present disclosure relates to a thermal index estimation system. Background Art

[0002] Wearable terminals are known that use a temperature sensor located within a housing to measure the temperature of the external space, which serves as a thermal indicator. In such wearable terminals, a temperature difference may occur between the internal space of the housing and the temperature of the space outside the housing due to, for example, sunlight exposure to the housing. Patent Document 1 describes a wearable terminal comprising a housing defining an internal space, a temperature sensor located within the internal space, and a heat-conductive member that contacts the temperature sensor and is exposed to the outside of the housing.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2016-206024 Summary of the Invention

[0006] Technical problem to be solved by the invention

[0007] In the wearable terminal described in Patent Document 1, a thermally conductive component functions as a heat conduction path connecting a temperature sensor located within the housing to the space outside the housing. This reduces the temperature difference between the interior and exterior of the housing, enabling the temperature outside the housing to be measured with high accuracy using the temperature sensor located within the housing. However, this requires a complex structure, with one end of the thermally conductive component in contact with the temperature sensor and the other end exposed to the exterior of the housing.

[0008] The present disclosure provides a thermal index estimating system for estimating a thermal index in an external space with a simple structure.

[0009] Solutions for solving technical problems

[0010] One aspect of the present disclosure relates to a thermal index estimation system comprising: a shell that defines an internal space and is provided with a vent hole that connects the internal space and a space outside the shell; a temperature measuring unit that is arranged in the shell and measures the temperature of the internal space; a detection unit that detects motion information indicating the movement of the shell; a light quantity measuring unit that measures the amount of light received by the shell; and an estimation unit that estimates the thermal index in the external space based on the temperature of the internal space, the motion information, and the light quantity.

[0011] When estimating the thermal index of the space outside the housing using the temperature of the housing's interior space, the aforementioned temperature difference between the interior and exterior spaces of the housing must be considered. This temperature difference may depend on the amount of air exchanged between the two spaces through the vents and the amount of light received by the housing. Furthermore, this air volume may depend on the movement of the housing. For example, if the housing moves violently, the air volume may increase. In this thermal index estimation system, the thermal index of the exterior space is estimated based on the temperature of the housing's interior space, motion information indicating the housing's motion, and the amount of light received by the housing. In other words, when estimating the thermal index of the exterior space, this thermal index estimation system considers the housing's motion information and the amount of light received by the housing, which may affect the temperature difference between the interior and exterior spaces of the housing. Therefore, the thermal index of the exterior space can be estimated without providing a component that functions as a heat conduction path connecting the interior and exterior spaces of the housing. As a result, the thermal index of the exterior space can be estimated using a simple structure.

[0012] In some embodiments, the estimation unit may estimate the thermal index based on time-series data on the internal space temperature, time-series data on motion information, and time-series data on light intensity. As described above, while the motion information of the housing and the amount of light received by the housing may affect the temperature difference between the internal space and the space outside the housing, the motion of the housing and the amount of light received by the housing are not immediately reflected in this temperature difference. Therefore, by using time-series data on the internal space temperature, motion information, and light intensity, changes in the internal space temperature, motion information, and light intensity over a certain period of time can be taken into account. This improves the accuracy of estimating the thermal index in the external space.

[0013] In some embodiments, the estimation unit may estimate the thermal index using a statistical regression model that takes the temperature, motion information, and light intensity of the interior space as input and outputs the thermal index. In this case, by fully learning the statistical regression model, the accuracy of estimating the thermal index in the exterior space can be improved.

[0014] In some embodiments, the detection unit may also be comprised of an inertial sensor. The motion information may also include the acceleration of the housing. In this case, the acceleration of the housing significantly reflects the movement of the housing, thereby improving the accuracy of the estimation of the thermal index in the external space.

[0015] In some embodiments, the motion information may also include the direction of the housing's acceleration. The amount of air exchanged between the housing's interior and exterior through the vents may be more dependent on the housing's movement in the direction of the vent opening. If the motion information includes the direction of the housing's acceleration, the movement of the housing in the direction of the vent opening can be derived based on this acceleration. Therefore, by using the direction of the housing's acceleration as motion information, the accuracy of estimating the thermal index in the exterior space can be further improved.

[0016] In some embodiments, the thermal index estimation system may further include a filter disposed in the vent hole for removing foreign matter. In this case, the vent hole can be kept air-permeable while preventing foreign matter from entering the housing.

[0017] In some embodiments, other ventilation holes may be provided in the housing. The ventilation holes and other ventilation holes may also open in different directions. When estimating the thermal index in the external space, estimation errors may occur. The greater the temperature difference between the interior space of the housing and the space outside the housing, the greater the estimation error. When the ventilation holes and other ventilation holes open in different directions, the air circulates efficiently between the interior space of the housing and the space outside the housing, thereby reducing the temperature difference between the two spaces. This improves the accuracy of the estimation of the thermal index in the external space.

[0018] In some embodiments, the thermal index estimation system may further include a window portion, disposed within the housing and configured to transmit light from the external space to the internal space. The light quantity measurement unit may also be disposed within the housing. The window portion may also be disposed in a position that overlaps the light quantity measurement unit when viewed from above. In this case, because the light quantity measurement unit can measure the amount of light received by the housing through the window portion, the temperature measurement unit and the light quantity measurement unit can be housed within the same housing. This allows estimation of the thermal index in the external space using a simpler structure.

[0019] In some embodiments, the window portion may be formed of a concave lens. In this case, the light quantity measuring unit can receive light incident from a wider range of angles, thereby reducing the size of the window portion.

[0020] In some embodiments, the window portion may be formed by processing the housing into a thin wall. In this case, since the window portion and the housing can be formed integrally, the thermal index in the external space can be estimated with a simpler structure.

[0021] Effects of the Invention

[0022] According to the present disclosure, it is possible to estimate the thermal index in the external space with a simple structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a block diagram illustrating an example of a functional configuration of a thermal index estimation system according to an embodiment.

[0024] Figure 2 It shows Figure 1 The figure is a perspective view of the appearance of a measuring device included in the thermal index estimation system.

[0025] Figure 3 It is along Figure 2 Cross-sectional view along line III-III.

[0026] Figure 4 It shows Figure 1 The following is a timing diagram of a series of operations performed by the thermal index estimation system.

[0027] Figure 5 It shows Figure 2 A diagram showing a modified example of the measuring device shown.

[0028] Figure 6 It shows Figure 2 FIG. 5 is a diagram showing another modified example of the measuring device shown.

[0029] Figure 7 It shows Figure 2 A diagram showing yet another modified example of the measuring device shown. DETAILED DESCRIPTION

[0030] The following describes the embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be noted that in the accompanying drawings, the same reference numerals are used for the same elements, and repeated descriptions are omitted. In each figure, an XYZ coordinate system is sometimes shown. The Y-axis direction is a direction that intersects (is orthogonal in this case) the X-axis direction and the Z-axis direction. The Z-axis direction is a direction that intersects (is orthogonal in this case) the Y-axis direction and the Z-axis direction. In this embodiment, the X-axis direction is the left-right direction, the Y-axis direction is the front-back direction, and the Z-axis direction is the up-down direction. For ease of description, the terms "front", "back", "up", "down", "left" and "right" are used, but are not limited to these directions.

[0031] First, refer to Figures 1 to 3 , a thermal index estimation system involved in one embodiment is described. Figure 1 This is a block diagram illustrating an example of a functional configuration of a thermal index estimation system according to an embodiment. Figure 2 It shows Figure 1 The illustrated perspective view is an external view of a measuring device included in the thermal index estimating system. Figure 3 It is along Figure 2 It should be noted that, in Figure 3In the figure, shading is omitted to clearly illustrate each part.

[0032] Figure 1 The thermal index estimation system 1 shown is to estimate the external space R1 (refer to Figure 3 ) in the thermal index system. The external space R1 is, for example, located in the housing 16 (refer to Figure 2 ). A "thermal index" is an indicator that indicates the body's thermal balance, sensation of heat or cold, or the risk of heat stroke when a person is present in that space. Examples of thermal indices include the temperature of the external space, the wet bulb globe temperature (WBGT), the Universal Thermal Climate Index (UTCI), the predicted mean vote (PMV), the effective temperature (ET), and the standard effective temperature (SET). In this embodiment, the thermal index estimation system 1 estimates the temperature of the external space R1 as the thermal index in the external space R1.

[0033] To achieve the above-mentioned functions, the thermal index estimation system 1 includes a measuring device 10 and an estimating device 20. The measuring device 10 measures the various parameters required for estimating the thermal index in the external space R1. The estimating device 20 uses the various parameters measured by the measuring device 10 to estimate the thermal index in the external space R1. In this embodiment, the measuring device 10 and the estimating device 20 are connected via a communication network (not shown) so that they can communicate information with each other. The communication network can be either wired or wireless. For example, information communication between the measuring device 10 and the estimating device 20 can be achieved through wired communication based on a USB (Universal Serial Bus) connection or through wireless communication such as BLTE (Bluetooth (registered trademark) Low Energy). The measuring device 10 and the estimating device 20 are described in detail below.

[0034] First, the measurement device 10 will be described. In this embodiment, the measurement device 10 measures parameters necessary for estimating the temperature of the external space R1. The measurement device 10 is a portable device, and examples thereof include a wearable terminal, a smartphone, and a tablet terminal. Examples of wearable terminals include those that can be worn on the arm, such as a smartwatch; those that can be worn around the waist, such as a pedometer; and those that can be hung around the neck, such as a pendant.

[0035] like Figure 2 and Figure 3 As shown, the measuring device 10 includes a circuit board 11 , a temperature measuring unit 12 , a detection unit 13 , a light quantity measuring unit 14 , a control unit 15 , a housing 16 , a filter 17 , and a window 18 .

[0036] The circuit board 11 is a component for electrically connecting the temperature measuring unit 12, the detection unit 13, the light quantity measuring unit 14 and the control unit 15. Figure 3 As shown, in this embodiment, the temperature measuring unit 12, the detection unit 13, the light intensity measuring unit 14, and the control unit 15 are mounted on one surface of a circuit board 11, which is disposed within a housing 16. For example, a resist may be formed on the surface of the circuit board 11, or screen printing may be performed. In this case, the surface of the circuit board 11 has a glossy finish, thereby achieving a high reflectivity for light.

[0037] The temperature measuring unit 12 measures the temperature of the internal space R2 defined by the housing 16. In this embodiment, the temperature measuring unit 12 continuously measures the temperature of the internal space R2. In this disclosure, "continuously" includes not only continuous measurement but also measurement at predetermined time intervals. The temperature measuring unit 12 outputs the measured temperature of the internal space R2 to the control unit 15.

[0038] In this embodiment, the temperature measuring unit 12 is composed of a temperature sensor. The temperature sensor is, for example, a semiconductor temperature sensor. The temperature sensor may be a thermistor element, a platinum temperature measuring resistor, or a thermocouple.

[0039] The detection unit 13 detects motion information indicating the movement of the housing 16. This motion information includes the acceleration of the housing 16 and the direction of this acceleration. Therefore, the detection unit 13 detects the acceleration and direction of this acceleration as motion information. In this embodiment, the detection unit 13 continuously detects the motion information of the housing 16. The detection unit 13 outputs the detected motion information of the housing 16 to the control unit 15.

[0040] In this embodiment, the detection unit 13 is comprised of an inertial sensor. For example, the inertial sensor is a MEMS (Micro Electro Mechanical System) triaxial acceleration sensor. This triaxial acceleration sensor detects acceleration applied to the housing 16 in the left-right, front-back, and up-down directions. The inertial sensor can be a uniaxial acceleration sensor, a biaxial acceleration sensor, or a six-axis gyroscope sensor.

[0041] Light quantity measuring unit 14 measures the amount of light received by housing 16. The amount of light received by housing 16 includes, for example, the amount of sunlight received by housing 16. In this embodiment, light quantity measuring unit 14 continuously measures the amount of light received by housing 16. Light quantity measuring unit 14 outputs the measured amount of light to control unit 15.

[0042] In this embodiment, the light quantity measuring unit 14 is composed of a photosensor sensitive to light in the visible light region. The photosensor is composed of, for example, a photodiode. The light quantity measuring unit 14 may also be composed of a photosensor sensitive to light in the ultraviolet region or the infrared region.

[0043] The control unit 15 communicates with the estimation device 20 and comprehensively controls the measurement device 10. As described above, in this embodiment, the measurement device 10 and the estimation device 20 are connected via a communication network so that they can communicate with each other. Therefore, the control unit 15 communicates with the estimation device 20 via the communication network. The control unit 15 is comprised of, for example, a microcontroller.

[0044] The control unit 15 obtains various estimation time-series data. This estimation time-series data is used to estimate the temperature of the external space R1. Based on the measurement command received from the estimation device 20, the control unit 15 obtains the estimation time-series data and transmits the obtained estimation time-series data to the estimation device 20. The method for obtaining the estimation time-series data and the measurement command will be described later.

[0045] The housing 16 is a component for housing the circuit board 11, the temperature measuring unit 12, the detection unit 13, the light intensity measuring unit 14, and the control unit 15. Specifically, the circuit board 11, the temperature measuring unit 12, the detection unit 13, the light intensity measuring unit 14, and the control unit 15 are disposed within the housing 16. In this embodiment, the temperature measuring unit 12, the detection unit 13, the light intensity measuring unit 14, and the control unit 15 are disposed on the circuit board 11 within the housing 16. The housing 16 is formed of a plastic resin and metal.

[0046] like Figure 2 As shown, the housing 16 has a flat, box-like shape and defines an internal space R2. In this embodiment, the corners and edges of the housing 16 are chamfered, but the corners and edges of the housing 16 may also be rounded. Alternatively, the housing 16 may have an entire arc. The housing 16 includes an upper wall 16a, a bottom wall 16b, side walls 16c, and an inclined wall 16d.

[0047] The upper wall portion 16a and the bottom wall portion 16b face each other in the vertical direction. The outer shape of the upper wall portion 16a is slightly smaller than that of the bottom wall portion 16b. The upper wall portion 16a and the bottom wall portion 16b have a square shape when viewed from above. The upper wall portion 16a and the bottom wall portion 16b may also have a rectangular shape when viewed from above.

[0048] The side wall portion 16c and the inclined wall portion 16d vertically connect the upper wall portion 16a and the bottom wall portion 16b. The side wall portion 16c is provided along the periphery of the bottom wall portion 16b, surrounding the bottom wall portion 16b. The side wall portion 16c is provided upright on the bottom wall portion 16b and extends from the bottom wall portion 16b toward the upper wall portion 16a. The inclined wall portion 16d connects the periphery of the upper wall portion 16a and the upper end of the side wall portion 16c. The inclined wall portion 16d is provided along the periphery of the upper wall portion 16a, surrounding the upper wall portion 16a.

[0049] The housing 16 is provided with a vent hole 16e. The vent hole 16e is a through hole that connects the interior space R2 and the exterior space R1. In this embodiment, two vent holes 16e are provided on the upper wall portion 16a, each vent hole 16e vertically penetrating the upper wall portion 16a. The two vent holes 16e open in the same direction. In this embodiment, both vent holes 16e open upward.

[0050] Filter 17 is a component used to remove foreign matter. Examples of foreign matter include liquids such as water, dust, and garbage. In this disclosure, "removing foreign matter" includes not only completely removing foreign matter but also reducing its amount. Filter 17 can also be said to be a component used to prevent foreign matter from entering housing 16.

[0051] The filter 17 is provided on the vent hole 16e so as to block the vent hole 16e. Therefore, in this embodiment, the measuring device 10 includes two filters 17. In this embodiment, in order to achieve the above functions, the filter 17 has air permeability and waterproof and dustproof functions.

[0052] The window portion 18 is light-transmissive and is a component for transmitting light received by the housing 16 and causing the light to enter the housing 16. The window portion 18 transmits light from the external space R1 to the internal space R2. The window portion 18 is provided in the housing 16. The window portion 18 is arranged at a position overlapping with the light quantity measuring unit 14 when viewed from above. In this case, the view from above refers to observing the window portion 18 from the thickness direction of the window portion 18. In this embodiment, the window portion 18 is provided in the upper wall portion 16a. The window portion 18 can be formed of a transparent acrylic plate or by processing the housing 16 into a thin wall.

[0053] In this embodiment, the window portion 18 is formed by a concave lens. The concave lens is formed of a transparent resin. Figure 3As shown, in this embodiment, the concave lens shape is formed by a Fresnel lens. The window portion 18 only needs to transmit the light received by the housing 16, and its structure is not limited to a concave lens. The window portion 18 can also be formed by a simple plate-shaped light incident plate.

[0054] Next, the estimation device 20 will be described. In the present embodiment, the estimation device 20 estimates the temperature of the external space R1 using various parameters measured by the measurement device 10.

[0055] Although not shown in the figure, the estimation device 20 is composed of, for example, one or more computers including a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), an input device, and an output device. Examples of the input device include a keyboard and a mouse. Examples of the output device include a display. The estimation device 20 realizes various functions by, for example, loading a program stored in the ROM into the RAM and executing the program loaded into the RAM by the CPU. Figure 1 As shown, the estimation device 20 functionally includes a communication unit 21 , a storage unit 22 , an estimation unit 23 , and an output unit 24 .

[0056] The communication unit 21 is a portion that transmits predetermined information to the measurement device 10 and receives information transmitted from the measurement device 10 .

[0057] The storage unit 22 stores various information used or generated by the estimation device 20. In this embodiment, the storage unit 22 stores various estimation time-series data, an estimation model, and estimation results from the estimation unit 23. The estimation model is a statistical regression model used to estimate the thermal index of the external space R1. As described above, in this embodiment, since the estimation device 20 estimates the temperature of the external space R1, the estimation model is a statistical regression model used to estimate the temperature of the external space R1.

[0058] The estimation unit 23 estimates the thermal index of the external space R1 based on the temperature of the internal space R2, the motion information of the housing 16, and the amount of light received by the housing 16. The estimation unit 23 estimates the temperature of the external space R1 as the thermal index of the external space R1. In this embodiment, the estimation unit 23 estimates the temperature of the external space R1 using the estimation model described above.

[0059] The output unit 24 is a component that outputs the estimation results. In this embodiment, the output unit 24 outputs the temperature of the external space R1 estimated by the estimation unit 23 as the estimation result. For example, the output unit 24 causes the estimation result to be displayed on the output device (display) of the estimation device 20. The output unit 24 may also output various estimation time-series data input to the estimation model along with the estimation result.

[0060] An example of a method for generating an estimation model will be described. First, the measuring device 10 is attached to a person or a robotic arm simulating a human arm. The temperature measuring unit 12, the detection unit 13, and the light intensity measuring unit 14 continuously perform measurements and detections, and these values ​​are stored in a memory (not shown) within the measuring device 10. Simultaneously, another measuring device with a temperature measurement function continuously measures and records the temperature of the external space R1. For example, this other measuring device may be configured such that a temperature sensor is directly exposed within the external space R1. This other measuring device may be placed within the external space R1 or, similarly to the measuring device 10, attached to a person or a robotic arm simulating a human arm.

[0061] Next, data for a predetermined period is extracted from the time series data of the temperature, motion information, and light amount of the internal space R2 stored in the above-mentioned memory. Next, data on the temperature of the external space R1 at a certain moment in the above-mentioned predetermined period is extracted from the time series data of the temperature of the external space R1. This moment is, for example, the latest moment in the above-mentioned predetermined period. Then, a combination of the extracted time series data of the temperature, motion information, and light amount of the internal space R2 and the temperature data of the external space R1 is generated. The combination of the generated data can be used as training data for learning the estimation model. The estimation model is generated by performing machine learning based on the training data generated in this way. For example, a recurrent neural network (RNN) is used as a statistical regression model.

[0062] Another example of a method for generating an estimation model will be described. First, a coupled analytical simulation can be performed to analyze heat transfer between the internal space R2 and the external space R1 within the measurement device 10, and temperature changes in the internal space R2 caused by the motion information of the housing 16 and the amount of light received by the housing 16. Based on the simulation results, time-series data of the calculated values ​​of the temperature, motion information, and light intensity of the internal space R2 is generated. The corresponding time-series data of the temperature of the external space R1 is also calculated.

[0063] Next, similar to the above method, data for a predetermined period is extracted from the generated time series data for the temperature, motion information, and light intensity of the internal space R2, and data for a specific moment is extracted from the time series data for the temperature of the external space R1. Training data is then generated, comprising a combination of the extracted time series data for the temperature, motion information, and light intensity of the internal space R2 and the temperature data of the external space R1. An estimation model can also be generated by performing machine learning based on the training data thus generated. This method allows for the generation of a larger amount of training data, even without conducting actual measurements. It should be noted that both the training data generated through actual measurements and the training data generated through simulation can be used for machine learning.

[0064] Next, refer to Figure 4 , the thermal index estimation method performed by the thermal index estimation system 1 is described. Figure 4 It shows Figure 1 The following is a timing diagram of a series of operations performed by the thermal index estimation system. Figure 4 The series of actions shown is initiated, for example, by a user operating an input device of estimation device 20 to input a measurement command into estimation device 20. In this embodiment, the measurement command includes a start time and an end time. It should be noted that in measurement device 10, temperature measuring unit 12 continuously measures the temperature of internal space R2, detection unit 13 continuously detects motion information of housing 16, and light intensity measuring unit 14 continuously measures the amount of light received by housing 16.

[0065] like Figure 4 As shown, first, the estimation device 20 receives a measurement instruction input by the user (step S1 ). Next, the communication unit 21 transmits the measurement instruction to the measurement device 10 (step S2 ).

[0066] Next, upon receiving the measurement command from the estimation device 20, the control unit 15 of the measurement device 10 obtains time-series data for estimation (step S3). In step S3, the control unit 15 samples the temperature of the internal space R2 measured by the temperature measurement unit 12, the motion information detected by the detection unit 13, and the light intensity measured by the light intensity measurement unit 14 during the measurement period from the start time to the end time, and stores the samples in a memory (not shown). This allows the control unit 15 to obtain time-series data for estimating the temperature of the internal space R2, the motion information, and the light intensity.

[0067] Next, the control unit 15 transmits each estimation time-series data item to the estimation device 20 (step S4). Upon receiving each estimation time-series data item from the measurement device 10, the communication unit 21 of the estimation device 20 outputs the received estimation time-series data item to the estimation unit 23. At this time, the communication unit 21 may also store the received estimation time-series data item in the storage unit 22.

[0068] Next, the estimation unit 23 estimates a thermal index for the external space R1 based on the temperature of the internal space R2, the motion information of the housing 16, and the amount of light received by the housing 16 (step S5). In this embodiment, the temperature of the external space R1 is estimated as the thermal index for the external space R1. In step S5, to estimate the temperature of the external space R1 at a given moment, the estimation unit 23 extracts data for a predetermined period from the time-series data for estimating the temperature of the internal space R2, the time-series data for estimating the motion information of the housing 16, and the time-series data for estimating the amount of light received by the housing 16. The estimation unit 23 then inputs the extracted time-series data for estimating the predetermined period into an estimation model to calculate an estimated value for the temperature of the external space R1 at the given moment. The predetermined period is set, for example, based on the time it takes for both the motion information of the housing 16 and the amount of light received by the housing 16 to be reflected in the temperature measured by the temperature measuring unit 12. The predetermined period can range from tens of seconds before the given moment to tens of seconds at the given moment, or from several minutes before the given moment to several minutes at the given moment. By performing this process on data at all times, time series data of estimated values ​​of the temperature of the external space R1 is obtained as an output.

[0069] Specifically, in step S5, the estimation unit 23 estimates the temperature of the external space R1 using a statistical regression model, i.e., an estimation model, for estimating the thermal index (temperature) of the external space R1. The estimation unit 23 outputs the estimated time-series data of the temperature of the external space R1 (estimated values) as estimation results to the storage unit 22 and the output unit 24.

[0070] Next, the output unit 24 outputs the estimation result (step S6). In step S6, upon receiving the estimation result from the estimation unit 23, the output unit 24 causes the estimation device 20 to display the estimation result on its output device (display). The output unit 24 may also display the estimation result on its display (display device) along with the estimation time-series data input to the estimation model.

[0071] As described above, the thermal index estimating system 1 estimates the thermal index (temperature) of the external space R1 based on the temperature of the internal space R2, motion information indicating the movement of the housing 16, and the amount of light received by the housing 16. When estimating the thermal index (temperature) of the external space R1 using the temperature of the internal space R2, it is necessary to consider the temperature difference between the internal space R2 and the external space R1. This temperature difference may depend on the amount of air exchanged between the internal space R2 and the external space R1 through the vents 16e and the amount of light received by the housing 16. Furthermore, this air volume may depend on the movement of the housing 16. For example, if the movement of the housing 16 is intense, the air volume may increase.

[0072] In the thermal index estimating system 1, when estimating the thermal index (temperature) in the external space R1, information about the movement of the housing 16 and the amount of light received by the housing 16, which may affect the temperature difference between the internal space R2 and the external space R1, are taken into account. Therefore, the thermal index (temperature) in the external space R1 can be estimated without providing a component that functions as a heat conduction path connecting the internal space R2 and the external space R1. As a result, the thermal index (temperature) in the external space R1 can be estimated using a simple configuration.

[0073] The estimation unit 23 estimates the thermal index (temperature) of the external space R1 based on time-series data on the temperature of the internal space R2, time-series data on the movement of the housing 16, and time-series data on the amount of light received by the housing 16. While the movement of the housing 16 and the amount of light received by the housing 16 may affect the temperature difference between the internal space R2 and the external space R1, these changes are not immediately reflected in this temperature difference. Therefore, by using time-series data on the temperature, movement, and light amount of the internal space R2 over a certain period, changes in these information can be taken into account. This improves the accuracy of the estimation of the thermal index (temperature) of the external space R1.

[0074] The estimation unit 23 estimates the temperature of the external space R1 using a statistical regression model, or estimation model. This statistical regression model receives as input time-series data on the temperature of the internal space R2, time-series data on the movement of the housing 16, and time-series data on the amount of light received by the housing 16, and outputs time-series data on the temperature of the external space R1. Therefore, by fully learning this estimation model, the accuracy of the estimation of the temperature of the external space R1 can be improved.

[0075] The detection unit 13 is comprised of an inertial sensor. To detect motion information of the housing 16, a wind speed sensor or velocity sensor could also be used to form the detection unit 13. However, since these sensors are larger than inertial sensors, the housing 16 would likely be larger. In the thermal index estimation system 1, since the detection unit 13 is comprised of an inertial sensor, it can be easily positioned within the housing 16.

[0076] The motion information detected by the detection unit 13 includes the acceleration of the housing 16. Since the acceleration of the housing 16 clearly reflects the motion of the housing 16, the estimation accuracy of the thermal index (temperature) in the external space R1 can be improved.

[0077] Movement information includes the direction of the acceleration of the housing 16. The amount of air exchanged between the interior space R2 and the exterior space R1 through the vents 16e may be more dependent on the movement of the housing 16 in the direction of the opening of the vents 16e. If the movement information includes the direction of the acceleration of the housing 16, the movement of the housing 16 in the direction of the opening of the vents 16e can be derived based on this direction of acceleration. Therefore, by using the direction of the acceleration of the housing 16 as movement information, the accuracy of estimating the thermal index (temperature) in the exterior space R1 can be further improved.

[0078] The filter 17 is provided in the vent hole 16e. Therefore, it is possible to prevent foreign matter from entering the housing 16 while ensuring air permeability in the vent hole 16e.

[0079] The temperature measuring unit 12, the detection unit 13, and the light quantity measuring unit 14 are arranged in the housing 16. Therefore, since the temperature measuring unit 12, the detection unit 13, and the light quantity measuring unit 14 are housed in the housing 16, the thermal index (temperature) in the external space R1 can be estimated with a simpler structure than a structure in which the detection unit 13 and the light quantity measuring unit 14 are arranged in a housing separate from the housing 16.

[0080] Window 18 is formed of a concave lens. Therefore, light measurement unit 14 can receive light incident from a wider range of angles. This allows the size of window 18 to be reduced. The smaller the size of window 18, the less light enters internal space R2. Therefore, reducing the size of window 18 can prevent a temperature increase in circuit board 11.

[0081] A resist is formed on the surface of the circuit board 11 and screen printing is performed. Therefore, the reflectivity of the circuit board 11 can be increased, and the temperature of the circuit board 11 can be prevented from rising due to sunlight.

[0082] Next, refer to Figure 5 , the configuration of a modified example of the thermal index estimating system 1 according to the present embodiment will be described. Figure 5 It shows Figure 2 FIG. 1 is a diagram showing a modified example of the measuring device shown. Figure 5 In, also with Figure 3 Likewise, hatching is omitted to clearly illustrate each component. The measurement device 10 according to this modification differs from the measurement device 10 according to the above embodiment mainly in the position of the vent hole 16e.

[0083] like Figure 5 As shown, in this variation, the two vent holes 16e open in different directions. Specifically, one of the two vent holes 16e is provided in the upper wall portion 16a and vertically penetrates the upper wall portion 16a. The other of the two vent holes 16e is provided in the side wall portion 16c and horizontally penetrates the side wall portion 16c. It should be noted that if the two vent holes 16e open in different directions, they can be provided in any of the upper wall portion 16a, the bottom wall portion 16b, the side wall portion 16c, and the inclined wall portion 16d.

[0084] Next, refer to Figure 6 , the configuration of another modified example of the thermal index estimating system 1 according to the present embodiment will be described. Figure 6 It shows Figure 2 FIG. 1 is a diagram showing another variation of the measuring device shown in FIG. Figure 6 In, also with Figure 3 and Figure 5 Likewise, hatching is omitted to clearly illustrate each component. The measurement device 10 according to this modification differs from the measurement device 10 according to the above embodiment mainly in the shape of the housing 16 and the position of the vent hole 16e.

[0085] like Figure 6 As shown, in this modification, the upper wall portion 16a and the inclined wall portion 16d have curvature. That is, in this modification, the upper wall portion 16a and the inclined wall portion 16d are curved so as to protrude toward the external space R1. As a result, the housing 16 as a whole has an arcuate shape.

[0086] In this variation, the two vent holes 16e also open in different directions. Specifically, the two vent holes 16e are provided in the upper wall portion 16a. The two vent holes 16e are provided at different positions on the upper wall portion 16a and extend through the upper wall portion 16a in a direction oblique to the vertical direction. It should be noted that in this variation, as long as the two vent holes 16e open in different directions, they can be provided in any of the upper wall portion 16a, the bottom wall portion 16b, the side wall portion 16c, and the inclined wall portion 16d.

[0087] When estimating the thermal index (temperature) in the external space R1, estimation errors may occur. The greater the temperature difference between the internal space R2 of the housing 16 and the external space R1 of the housing 16, the greater the estimation error. In each of the above-described variations, the two vent holes 16e open in different directions. This effectively circulates air between the internal space R2 and the external space R1, reducing the temperature difference between the two. This improves the accuracy of estimating the thermal index (temperature) in the external space R1.

[0088] Next, refer to Figure 7 The configuration of yet another modified example of the thermal index estimating system 1 according to the present embodiment will be described. Figure 7 It shows Figure 2 FIG. 1 is a diagram showing another variation of the measuring device shown in FIG. Figure 7 In, also with Figure 3 、 Figure 5 and Figure 6 Likewise, hatching is omitted to clearly illustrate each portion. The measurement device 10 according to this modification differs from the measurement device 10 according to the above embodiment mainly in the method of forming the window portion 18 .

[0089] In this variation, window 18 is formed by processing housing 16 into a thinner wall. As described above, housing 16 is composed of plastic resin and metal. In this variation, window 18 is formed by processing the plastic resin constituting housing 16 into a thinner wall, and housing 16 and window 18 are integrally formed.

[0090] In this variation, because housing 16 and window 18 can be integrally formed, the thermal index in external space R1 can be estimated with a simpler structure. Furthermore, in this variation, even if housing 16 and window 18 are made of opaque materials, light received by housing 16 will pass through window 18. Therefore, even if housing 16 and window 18 are made of opaque materials, light measurement unit 14 can still measure the amount of light received by housing 16.

[0091] The present disclosure is not limited to the above-described embodiment and modified examples, and various changes can be made without departing from the spirit and scope of the present disclosure.

[0092] In the above-described embodiment and variations, the temperature measuring unit 12, the detection unit 13, and the light intensity measuring unit 14 are arranged within the same housing 16. However, the arrangement of the temperature measuring unit 12, the detection unit 13, and the light intensity measuring unit 14 is not limited to the above arrangement. For example, the temperature measuring unit 12 and the light intensity measuring unit 14 may be arranged within the housing 16, while the detection unit 13 is arranged within a housing different from the housing 16. Alternatively, the temperature measuring unit 12 and the detection unit 13 may be arranged within the housing 16, while the light intensity measuring unit 14 is arranged within a housing different from the housing 16. Alternatively, the temperature measuring unit 12 may be arranged within the housing 16, while the detection unit 13 and the light intensity measuring unit 14 may be arranged within a housing different from the housing 16. If the detection unit 13 is arranged within a housing different from the housing 16, the housing may be worn closer to the housing 16. For example, if the housing 16 is worn on a person's arm, the housing may also be worn on the arm on which the housing 16 is worn. Thus, even if the detection unit 13 is arranged in a housing different from the housing 16 , the motion information detected by the detection unit 13 can be regarded as the motion information of the housing 16 .

[0093] In the above-described embodiment and modified examples, the number of vent holes 16e is "two", but it may be "one" or "three" or more. When the number of vent holes 16e is "three" or more, at least two of the three or more vent holes 16e may open in different directions.

[0094] In the above-described embodiment and modified example, the filter 17 is provided at the vent hole 16e so as to block the vent hole 16e. However, the filter 17 may not be provided at the vent hole 16e. In other words, the measuring device 10 may not include the filter 17.

[0095] In the above-mentioned embodiments and modifications, the motion information of the shell 16 includes the acceleration of the shell 16 and the direction of the acceleration. However, the parameters included in the motion information of the shell 16 are not limited to the above-mentioned parameters (the acceleration of the shell 16 and the direction of the acceleration). For example, the motion information of the shell 16 may also include the speed of the shell 16 and the direction of the speed instead of the acceleration of the shell 16 and the direction of the acceleration. In this case, the detection unit 13 may also be composed of a speed sensor. Alternatively, the motion information of the shell 16 may also include the wind speed of the air ventilated between the internal space R2 and the external space R1 through the vent 16e and the direction of the wind speed instead of the acceleration of the shell 16 and the direction of the acceleration. In this case, the detection unit 13 may also be composed of a wind speed sensor.

[0096] In the above-described embodiment and variations, the estimation unit 23 estimates the temperature of the external space R1 based on the temperature of the internal space R2, the motion information of the housing 16, and the amount of light received by the housing 16. However, the parameters used to estimate the temperature of the external space R1 are not limited to the above parameters (the temperature of the internal space R2, the motion information of the housing 16, and the amount of light received by the housing 16). When a person is carrying the measurement device 10, the estimation unit 23 may estimate the temperature of the external space R1 based on the type of activity performed by the person, in addition to the above parameters. In this case, the type of activity may be input to the estimation device 20 by the user via an input device. Alternatively, the estimation unit 23 may determine the type of activity based on the motion information of the housing 16 detected by the detection unit 13.

[0097] "Activity type" indicates the state of movement being performed by the person wearing the measurement device 10 when measuring various parameters. Examples of activity types include walking, running, and cycling. When the estimation unit 23 estimates the temperature of the external space R1 based on the temperature of the internal space R2, motion information from the housing 16, the amount of light received by the housing 16, and the type of activity, the storage unit 22 may store multiple estimation models corresponding to the type of activity. The estimation unit 23 may also estimate the temperature of the external space R1 using the estimation model corresponding to the type of activity.

[0098] In the above-described embodiment and variations, the estimation unit 23 estimates the temperature of the external space R1 using an estimation model. This estimation model receives as input time-series data on the temperature of the internal space R2, time-series data on the motion of the housing 16, and time-series data on the amount of light received by the housing 16, and outputs time-series data on the temperature of the external space R1. However, the estimation model does not necessarily need to use time-series data as input.

[0099] For example, the estimation unit 23 may estimate the temperature of the external space R1 using an estimation model that takes as input the temperature of the internal space R2 at a certain moment (measurement moment), the motion information of the housing 16, and the amount of light received by the housing 16, and outputs the temperature of the external space R1. The control unit 15 may sample the temperature of the internal space R2 measured by the temperature measuring unit 12, the motion information detected by the detection unit 13, and the amount of light measured by the light intensity measuring unit 14 at each measurement moment, and store the samples in a memory (not shown). The estimation model may also be generated by performing machine learning based on correct answer data, where the correct answer data includes a combination of the temperature of the internal space R2, the motion information of the housing 16, the amount of light received by the housing 16 at each measurement moment, and the actual measured value of the temperature of the external space R1 at the measurement moment. In this case, by fully learning the estimation model, the accuracy of the estimation of the thermal index (temperature) in the external space R1 can be improved.

[0100] In the above-described embodiment and variations, the estimation unit 23 estimates the temperature in the external space R1 using an RNN, a type of statistical regression model. However, the method for estimating the thermal index (temperature) is not limited to methods using an RNN. For example, the estimation unit 23 may also use another statistical regression model to estimate the temperature in the external space R1. In this case, the other statistical regression model is generated by performing regression analysis or parameter fitting using the temperature of the internal space R2, the motion information of the housing 16, and the amount of light received by the housing 16, or their time-series data, as explanatory variables, and the temperature of the external space R1 or its time-series data as the target variable. Examples of such other statistical regression models include linear models, generalized linear models, vector autoregression models, neural networks (including neural networks without a recursive structure like an RNN), support vector regression models, random forests, and extreme gradient boosting (XGboost) models.

[0101] Alternatively, the estimation unit 23 may not rely on a statistical regression model but may instead physically model the temperature-related phenomena in the measuring device 10, calculate the temperature difference between the temperature of the internal space R2 and the temperature of the external space R1, and estimate the temperature of the external space R1 based on the temperature of the internal space R2 and the temperature difference. To physically model the temperature-related phenomena, for example, a thermal equivalent circuit may be used. This thermal equivalent circuit replaces the heat transfer between the internal space R2 and the external space R1 in the measuring device 10 with an electronic circuit. Among the parameters of the elements constituting the thermal equivalent circuit, parameters whose values ​​vary due to the movement of the housing 16 and the amount of light received by the housing 16 may also be varied based on information about the movement of the housing 16 and the amount of light received by the housing 16.

[0102] The measurement device 10 may also include the functions of the estimation device 20 (storage unit 22, estimation unit 23, and output unit 24). For example, the control unit 15 may also function as the storage unit 22, estimation unit 23, and output unit 24. Specifically, the control unit 15 may estimate the thermal index (temperature) in the external space R1 based on the temperature of the internal space R2, the motion information of the housing 16, and the amount of light received by the housing 16, and output the estimated result. Furthermore, the measurement device 10 may also physically include an input device for receiving user input and a display (display device) for displaying the estimated result.

[0103] In the above-described embodiment and variations, the estimating unit 23 estimates the temperature of the external space R1 as a thermal index. However, the estimated thermal index may also be another index, such as the wet-bulb globe temperature, UTCI, estimated mean thermal sensation index, effective temperature, or standard effective temperature. In this case, since humidity and water vapor pressure also contribute to the thermal index, the estimating unit 23 may also estimate the thermal index based on the humidity and air pressure of the internal space R2, in addition to the temperature of the internal space R2, motion information of the housing 16, and the amount of light received by the housing 16. In this case, the measuring device 10 may also include a humidity sensor and an air pressure sensor.

[0104] Furthermore, when a person carries the measuring device 10, the amount of clothing and metabolic rate of the person also contribute to the above-mentioned thermal index. The above-mentioned metabolic rate varies depending on age and gender. For example, there is a tendency that the older the age, the lower the metabolic rate, and that women have lower metabolic rates than men. Therefore, in addition to the various parameters mentioned above, the estimation unit 23 can also estimate the above-mentioned thermal index based on at least one of the amount of clothing, age and gender of the person carrying the measuring device 10. In this case, the above-mentioned amount of clothing, age and gender can also be input into the estimation device 20 by the user in advance via the input device and stored in the storage unit 22. It should be noted that when estimating a thermal index other than the temperature of the external space R1, the temperature of the external space R1 in the training data used to learn the estimation model is replaced with the measured value or simulated value of the estimated thermal index to implement learning.

[0105] The estimation model may also be fed with data (feature quantities) obtained by preprocessing the various parameters obtained by the measurement device 10. For example, if the motion information of the housing 16 includes the acceleration of the housing 16, the time series data of this acceleration may be preprocessed to calculate a predetermined index for each fixed interval, and this index may be used in place of the acceleration of the housing 16 to estimate the thermal index. This preprocessing may be performed by the control unit 15.

[0106] Examples of the aforementioned indicators include ZC (Zero Crossings), TAT (Time Above the Threshold), and PI (Proportional Integration). ZC is an indicator that indicates the number of times the acceleration value crosses a predetermined value in the time series data. TAT is an indicator that indicates the total time that the acceleration value is above a predetermined threshold in the time series data. PI is an indicator that indicates the area of ​​the region enclosed by a curve representing the time series data of the acceleration of the housing 16 and a curve representing a fixed acceleration value, when considering a two-dimensional coordinate system with the acceleration value on the vertical axis and time on the horizontal axis. Any of the aforementioned indicators can be used as an indicator that indicates the degree of movement of the housing 16.

[0107] When the above-mentioned indices are used in place of the acceleration of the housing 16 to estimate the thermal index of the external space R1, a memory (not shown) within the measurement device 10 stores time-series data of the above-mentioned indices as time-series data for estimating the motion information of the housing 16. Because these indices are represented by a single numerical value for a fixed interval, the data volume is smaller than that of the time-series data of the acceleration of the housing 16. This saves storage capacity within the memory of the measurement device 10. However, this preprocessing and index calculation does not necessarily need to be performed in the control unit 15; they can also be performed within the estimation device 20.

[0108] Description of Reference Numerals

[0109] 1: Thermal index estimation system; 12: Temperature measurement unit; 13: Detection unit; 14: Light intensity measurement unit; 16: Housing; 16e: Ventilation hole; 17: Filter; 18: Window; 23: Estimation unit; R1: External space; R2: Internal space.

Claims

1. A thermal index estimation system comprising: a shell defining an internal space and provided with a vent hole communicating the internal space with a space outside the shell; a temperature measuring unit disposed in the housing and measuring the temperature of the internal space; a detection unit that detects motion information indicating the motion of the housing; a light quantity measuring unit for measuring the quantity of light received by the housing; as well as The estimating unit estimates a thermal index in the external space based on the temperature of the internal space, the motion information, and the light amount.

2. The thermal index estimation system according to claim 1, wherein: The estimation unit estimates the thermal index based on time-series data of the temperature of the internal space, time-series data of the motion information, and time-series data of the light amount.

3. The thermal index estimation system according to claim 1 or 2, wherein: The estimation unit estimates the thermal index using a statistical regression model. The statistical regression model takes the temperature of the internal space, the motion information, and the light amount as inputs and outputs the thermal index.

4. The thermal index estimation system according to any one of claims 1 to 3, wherein: The detection unit is composed of an inertial sensor, The motion information includes acceleration of the housing.

5. The thermal index estimation system according to claim 4, wherein: The motion information further includes a direction of the acceleration of the housing.

6. The thermal index estimation system according to any one of claims 1 to 5, wherein: The thermal index estimation system further includes a filter provided in the vent hole and configured to remove foreign matter.

7. The thermal index estimation system according to any one of claims 1 to 6, wherein: Other vent holes are provided in the housing. The vent hole and the other vent holes are opened in different directions.

8. The thermal index estimation system according to any one of claims 1 to 7, wherein: The thermal index estimation system further includes a window portion, which is provided in the housing and transmits light from the external space to the internal space. The light quantity measuring unit is arranged in the housing. The window portion is arranged at a position overlapping with the light intensity measurement unit in a plan view.

9. The thermal index estimation system according to claim 8, wherein: The window portion is formed of a concave lens.

10. The thermal index estimation system according to claim 8 or 9, wherein: The window portion is formed by processing the housing into a thin wall.

Images