Thermal environment measuring device, and thermal environment analysis method employing same

Abstract

The objective of the present invention is to realize a technique capable of automatically measuring a thermal environment of a target space in all directions using a relatively simple means.　A thermal environment measuring device according to the present disclosure is a device that measures the thermal environment of a target space in all directions by rotating a plurality of detectors around a plurality of axes. The measuring device 1 comprises motors 4, a housing portion 10, and a rotating portion 20. Furthermore, the plurality of detectors include: an infrared sensor 2 for measuring infrared radiation of an object within the target space; and a distance measuring sensor 3 for measuring the distance to the object by emitting laser light onto the object within the target space and receiving reflected light reflected from the object. In addition, the housing portion 10 is rotated around a predetermined first axis by a first motor 41 constituting the motors 4, and the rotating portion 20 is rotated around a second axis substantially orthogonal to the first axis by a second motor 42 constituting the motors 4.

Description

Thermal environment measuring device and thermal environment analysis method using the same

[0001] The present invention relates to a thermal environment measuring device that measures the thermal environment of a target space in all directions by rotating multiple detectors around multiple axes, and a thermal environment analysis method using the same.

[0002] Conventionally, the thermal environment inside a building has been measured by using a temperature sensor to measure the temperature of the space or an infrared sensor to measure the temperature of any part of the wall, and the environmental performance of the building has been simulated.

[0003] Meanwhile, when designing a building, the location of ventilation and air conditioning devices, the amount of insulation material used and its placement, etc. are set in consideration of the living environment, such as the size and layout of each room, the outside temperature, and the amount of solar radiation. There is known a technique for simulating the thermal environment for each room of a building designed and constructed in this way.

[0004] For example, Patent Document 1 discloses a building thermal environment simulation device that can simulate the winter thermal environment of each room in a building with simple operations. In this thermal environment simulation device, information about each room in a building is stored in a storage means, and based on this information, the heat loss coefficient, summer solar gain coefficient, and winter solar gain coefficient for each room can be calculated. This allows the thermal environment, such as the average room temperature, to be simulated.

[0005] JP 2013-41591 A

[0006] In conventional thermal environment measurements using sensors, the environmental performance of a target space is often simulated by treating the temperature of an arbitrary portion of the wall defining the target space as a representative temperature of the wall. In this case, for example, if there is a bias in the amount of insulation used or its placement, it may be difficult to accurately predict the environmental performance of the target space. On the other hand, even if conventional infrared sensors are used to measure the walls of a target space in all directions, the temperature detected by the infrared sensor is only two-dimensional information within a certain measurement range, making it often difficult to identify the location in the target space that has that temperature information. Furthermore, measuring the temperature of multiple walls using such conventional sensors requires the user to manually adjust the direction of infrared radiation, resulting in significant time-consuming temperature measurement.

[0007] For example, the technology described in Patent Document 1 appears to be able to accurately simulate the thermal environment of a building based on stored information. However, the information for each room in the building used in the technology described in Patent Document 1 is limited to the area and heat transfer coefficient of the floor, ceiling, exterior walls, etc., the opening area and heat transfer coefficient of windows, etc., an orientation coefficient corresponding to the orientation of the windows and exterior walls, and a coefficient indicating the degree of contact with the outside air, but does not take into account the placement of insulation on the walls of each room. Furthermore, if one were to pre-store information on the physical properties of the walls defining the target space to be simulated in all directions, it would ultimately be necessary to measure the temperature of the walls in all directions. Furthermore, if conventional infrared sensors were used to measure the walls in all directions in the target space, the above-mentioned problems could arise.

[0008] Therefore, an object of the present disclosure is to realize a technology that can automatically measure the thermal environment of a target space in all directions using relatively simple means.

[0009] The thermal environment measuring device disclosed herein measures the thermal environment of a target space in all directions by rotating multiple detectors around multiple axes. The thermal environment measuring device includes a motor for rotating the multiple detectors around the multiple axes, a housing that houses the motor, a power supply, and an electronic board, and a rotating unit that is journaled on the housing and houses the multiple detectors and a sensor board that serves as their board. The multiple detectors include an infrared sensor that measures infrared radiation from an object in the target space, and a distance sensor that measures the distance to the object by irradiating the object with laser light and receiving light reflected from the object. The housing is rotated around a predetermined first axis by a first motor that constitutes the motor, and the rotating unit is rotated around a second axis that is approximately perpendicular to the first axis by a second motor that constitutes the motor.

[0010] The thermal environment measuring device described above can visualize, for example, temperature information of a wall defining a target space in three dimensions across all directions. Specifically, three-dimensional point cloud information of the target space is generated based on the distance to the wall measured by a distance sensor, and temperature information related to the temperature of the wall measured by an infrared sensor is mapped onto the three-dimensional point cloud, thereby visualizing the temperature information of the target space in three dimensions across all directions. Furthermore, in this thermal environment measuring device, the housing unit is automatically rotated left and right around a first axis and the rotating unit is automatically rotated up and down around a second axis using power from a motor, eliminating the need for the measurer to manually adjust the direction of infrared radiation. This simple configuration using only the measuring device can automatically measure the thermal environment of the target space in all directions. The thermal environment measuring device can also acquire multiple images of temperature information at each rotation angle and automatically visualize them as an omnidirectional image of the target space by overlaying them, thereby significantly reducing the effort required for temperature measurement.

[0011] In the thermal environment measuring device, the infrared sensor and the distance measuring sensor may be disposed substantially on the axis of the first axis and the second axis. This minimizes errors (parallax effect) caused by shifts in sensor viewpoint due to device rotation. The rotating unit may have shaft ends at both ends, the housing may have bearings for supporting the shaft ends of the rotating unit, and the sensor substrate may be configured to penetrate through the shaft ends from the rotating unit side of the bearing to the housing side, thereby incorporating a portion of the sensor substrate into the housing.

[0012] The present disclosure also provides a thermal environment analysis method using the thermal environment measuring device, which includes a first step of generating three-dimensional point cloud information representing the positions of three-dimensional points in the target space based on distances to objects in the target space measured by the ranging sensor, a second step of mapping temperature information relating to temperatures of objects in the target space measured by the infrared sensor onto the three-dimensional point cloud of the target space using the three-dimensional point cloud information, and a third step of visualizing the temperature information mapped onto the three-dimensional point cloud of the target space.

[0013] The thermal environment analysis method may further include a first evaluation step in which the second step maps the temperature information measured by the infrared sensor at a predetermined time and evaluates the thermal insulation and / or airtightness of the target space based on the temperature information visualized in the third step. The first evaluation step may further include a comfort evaluation step in which an up-down difference, which is the difference in thermal insulation in the vertical direction of the target space, and / or a left-right difference, which is the difference in thermal insulation in the horizontal direction of the target space, are calculated, and the comfort of a user in the target space is evaluated based on the up-down difference and / or the left-right difference. In this case, the comfort evaluation step further calculates an operative temperature affecting the user based on an average radiant temperature, which is the temperature radiated from objects in the target space, and evaluates the user's comfort based on the operative temperature. In the first evaluation step, if the difference between the operative temperature and the air temperature of the target space is equal to or greater than a predetermined threshold, it may be evaluated that heat transfer is occurring inside and outside the target space due to a lack of thermal insulation and / or airtightness of the target space.

[0014] The thermal environment analysis method may further include a second evaluation step in which, in the second step, the temperature information measured by the infrared sensor at predetermined time intervals is mapped for each measurement time, and in the third step, the temperature information mapped for each measurement time is visualized over time, and the thermal insulation and / or airtightness of the target space is evaluated based on the temperature information visualized in the third step. In this case, in the second evaluation step, the thermal insulation and / or airtightness of the target space may be evaluated as being deficient if the temperature change over time, which is the change over time of the temperature information visualized in the third step, is linked to the change in outside air temperature outside the target space. Alternatively, in the second evaluation step, the thermal insulation and / or airtightness of the target space may be evaluated as being deficient if the temperature change over time, which is the change over time of the temperature information visualized in the third step, shows a temperature difference in the vertical direction of the target space.

[0015] Furthermore, in the above-described thermal environment analysis method, in the second step, the temperature information measured by the infrared sensor at a predetermined time interval is mapped for each measurement time, and in the third step, the temperature information mapped for each measurement time is visualized over time, and the method may further include an estimation step of estimating physical properties, including thermal properties, of objects in the target space based on the temperature information visualized in the third step and the temperatures inside and outside the target space.

[0016] According to the present disclosure, a technology that can automatically measure the thermal environment of a target space in all directions can be realized using relatively simple means.

[0017] 1 is a diagram showing a schematic configuration of a thermal environment measuring device in a first embodiment. FIG. 2 is a diagram for explaining left-right rotation around a first axis using a first motor. FIG. 3 is a diagram for explaining up-down rotation around a second axis using a second motor. FIG. 4 is a diagram showing a usage mode of a measuring device that is rotated to measure the thermal environment of a target space in all directions. FIG. 5 is a diagram illustrating an example of a mode in which a cable connecting an electronic board and a sensor board is stored in a housing unit by having a sensor board pass through an end of the shaft. FIG. 6 is a first flowchart illustrating a processing flow in a thermal environment analysis method according to a second embodiment. FIG. 7 is a second flowchart illustrating a processing flow in a thermal environment analysis method according to a second embodiment. FIG. 8 is a diagram for explaining a neural network that constitutes a machine learning model.

[0018] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. The configurations of the following embodiments are examples, and the present disclosure is not limited to the configurations of the embodiments.

[0019] First Embodiment An overview of a thermal environment measuring device in a first embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing the schematic configuration of a thermal environment measuring device in this embodiment. Note that Fig. 1(a) shows a state in which covers for a housing unit and a rotating unit, which will be described later, are removed, and when this thermal environment measuring device is used, the housing unit and the rotating unit are covered with covers as shown in Fig. 1(b). In the following description, a target space represents, for example, a room in a building, and an object in the target space represents, for example, a wall surface or a window of the room.

[0020] The measuring device 1 according to this embodiment is a thermal environment measuring device that measures the thermal environment of a target space in all directions by rotating multiple detectors around multiple axes.

[0021] Here, the multiple detectors include an infrared sensor 2 and a distance measurement sensor 3. The infrared sensor 2 is a sensor that measures infrared radiation from an object in the target space, and can measure, for example, the temperature of the wall surface of the target space. The distance measurement sensor 3 is a so-called LiDAR (Light Detection and Ranging) sensor that measures the distance to an object in the target space by irradiating the object with laser light and receiving the light reflected from the object.

[0022] The measurement device 1 also includes a motor 4 that rotates the plurality of detectors around a plurality of axes. In this embodiment, the motor 4 is configured by a first motor 41 that rotates the plurality of detectors in the left-right direction around a first axis, and a second motor 42 that rotates the plurality of detectors in the up-down direction around a second axis. Note that the left-right rotation around the first axis using the first motor 41 will be described in detail with reference to FIG. 2 (described later), and the up-down rotation around the second axis using the second motor 42 will be described in detail with reference to FIG. 3 (described later).

[0023] The measuring device 1 also includes a housing 10 that houses a motor 4, a power supply 5, and an electronic board 6. The power supply 5 is a power source for the motor 4, the infrared sensor 2, and the distance measurement sensor 3, and the electronic board 6 is used to control the operations of these. As shown in FIG. 1 , the housing 10 is supported by a support 30.

[0024] The measurement device 1 includes a rotating unit 20 that is pivotally supported by the housing 10 and incorporates multiple detectors (infrared sensors 2, distance measuring sensors 3) and a sensor board 7 that serves as the substrate for those detectors. As shown in FIG. 1( a), the rotating unit 20 may incorporate a stereo camera 8. This makes it possible to acquire images of objects in the target space in addition to the temperature and distance to the objects measured by the multiple detectors. The configuration is not limited to the stereo camera 8, as long as it is capable of acquiring color images of objects in the target space.

[0025] 2 is a diagram for explaining left-right rotation about the first axis using the first motor 41. Note that Fig. 2 only illustrates the configuration for rotating the housing 10 left-right about the first axis using the first motor 41.

[0026] As shown in FIG. 2 , power from the first motor 41 is transmitted to a rotating shaft formed in the housing 10 via a belt and a pulley. More specifically, a pulley 412 is connected to an output shaft 411 of the first motor 41, and a belt 413 is wound around the pulley 412. The housing 10 also includes a rotating shaft 11 formed integrally with a support block 12 rigidly joined to the housing 10 so as to protrude from the support block 12, and a pulley 111 is connected to the rotating shaft 11 on the support block 12 side. The belt 413 is then wound around the pulley 111. This allows power from the first motor 41 to be transmitted to the rotating shaft 11 formed in the housing 10.

[0027] The end of the rotating shaft 11 protrudes downward from the housing 10. A bearing 31 is press-fitted into the upper end of the support 30. This allows the end of the rotating shaft 11 to be inserted into the bearing 31, and when the rotating shaft 11 is rotated by the power transmitted from the first motor 41, the housing 10 is rotated left and right around the first axis relative to the support 30.

[0028] 3 is a diagram for explaining the rotation in the up-down direction about the second axis using the second motor 42. Note that FIG. 3 only illustrates the configuration for rotating the rotating unit 20 in the up-down direction about the second axis using the second motor 42.

[0029] As shown in FIG. 3 , power from the second motor 42 is transmitted to the shaft end 210 of the rotating unit 20 via a belt and a pulley. More specifically, a pulley 422 is connected to the output shaft 421 of the second motor 42, and a belt 423 is wound around the pulley 422. Furthermore, shaft end portions 210 are provided on both left and right ends of the rotating unit 20 so as to protrude left and right from the rotating unit 20, and a pulley 211 is connected to one of the shaft end portions 210. The belt 423 is then wound around the pulley 211. In this way, power from the second motor 42 is transmitted to the shaft end portions 210 provided in the rotating unit 20.

[0030] Here, the housing 10 has a bearing 100 for supporting the shaft end 210 of the rotating part 20. Then, when the shaft end 210 of the rotating part 20 is rotated by the power transmitted from the second motor 42 while being supported by the bearing 100 of the housing 10, the rotating part 20 is caused to rotate in the vertical direction around the second axis relative to the housing 10.

[0031] In addition, in the measurement device 1 according to this embodiment, the infrared sensor 2 and the distance measurement sensor 3 may be disposed substantially on the axis of the first axis and the second axis, thereby eliminating or reducing the parallax effect that may occur due to rotation of the device.

[0032] FIG. 4 is a diagram showing a usage mode of the measurement device 1 that can be rotated to measure the thermal environment of a target space in all directions.

[0033] 4(a) is a diagram showing a state in which the infrared sensor 2 and the distance measurement sensor 3 are rotated left and right around the first axis, and as shown in this Fig. 4(a), by arranging the infrared sensor 2 and the distance measurement sensor 3 approximately on the axis line of the first axis, change in the viewpoint position of these sensors is suppressed as much as possible even when the measurement device 1 is rotated left and right around the first axis. As a result, for example, when multiple images of temperature information visualized using the above sensors are acquired for each rotation angle and then superimposed to visualize an omnidirectional image of the target space, errors (parallax effect) due to shifts in the sensor viewpoint that may occur due to device rotation can be suppressed as much as possible.

[0034] 4(b) is a diagram showing a state in which the infrared sensor 2 and the distance measurement sensor 3 are rotated up and down around the second axis, and by arranging the infrared sensor 2 and the distance measurement sensor 3 substantially on the axis line of the second axis as shown in this Fig. 4(b), even when the measurement device 1 rotates up and down around the second axis, changes in the viewpoint positions of these sensors are minimized, thereby minimizing the parallax effect.

[0035] Furthermore, in the measuring device 1 according to this embodiment, the sensor board 7 may be configured to penetrate through the shaft end portion 210 from the rotating portion 20 side of the bearing 100 to the housing portion 10 side, so that a portion of the sensor board 7 is built into the housing portion 10. This makes it possible to store the cable connecting the electronic board 6 and the sensor board 7 inside the housing portion 10, thereby minimizing cable interference as much as possible. This will be described with reference to FIG. 5 . Note that contact between the electronic board 6 and the sensor board 7, which will be described later, may be achieved by a slide contact.

[0036] FIG. 5 is a diagram illustrating an example in which the sensor board 7 passes through the shaft end portion 210, so that the cable connecting the electronic board 6 and the sensor board 7 is housed within the housing portion 10.

[0037] As shown in FIG. 5 , when the sensor board 7 penetrates the shaft end portion 210 from the rotating portion 20 side of the bearing 100 to the housing portion 10 side, the tip portion 7 a of the sensor board 7 is exposed inside the housing portion 10. The tip portion 7 a of the sensor board 7 is connected to the electronic board 6 by a cable 6 a, so that power, control signals, and the like are transmitted from the electronic board 6 to the sensor board 7. Here, the sensor board 7 rotates relative to the electronic board 6 as the rotating portion 20 rotates. Therefore, the cable connecting the electronic board 6 and the sensor board 7 is required to be flexible enough to accommodate the rotational movement. In this case, if the cable were exposed to the outside, there is a risk that the rotational movement would be hindered or the cable would break due to interference with the surroundings. In contrast, according to the embodiment illustrated in FIG. 5 , the cable 6 a, which flexibly moves in response to the rotational movement, is housed within the housing portion 10, thereby preventing the cable from interfering with the surroundings.

[0038] The temperature information of the wall surfaces defining the target space can be visualized three-dimensionally in all directions using the measurement device 1. More specifically, three-dimensional point cloud information of the target space is generated based on the distance to the wall surfaces of the target space measured by the distance measuring sensor 3, and temperature information related to the temperature of the wall surfaces of the target space measured by the infrared sensor 2 is mapped onto the three-dimensional point cloud, thereby making it possible to visualize the temperature information of the target space three-dimensionally in all directions.

[0039] Furthermore, in the above-described measuring device 1, the housing 10 is automatically rotated left and right around the first axis and the rotating part 20 is automatically rotated up and down around the second axis by power from the motor 4, so the measurer does not need to manually adjust the direction of infrared radiation, and the thermal environment of the target space can be automatically measured in all directions with a simple configuration using only the measuring device 1. In addition, the measuring device 1 can acquire multiple images of temperature information for each rotation angle and automatically visualize them as an omnidirectional image of the target space by superimposing them, thereby significantly reducing the effort required for temperature measurement.

[0040] Furthermore, the measurement device 1 described above can realize a technology that can automatically measure the thermal environment of a target space in all directions using relatively simple means.

[0041] Second Embodiment A thermal environment analysis method according to the second embodiment will be described below. The thermal environment analysis method according to this embodiment is an analysis method using the measurement device 1 described in the first embodiment above. In the following description, the target space represents, for example, a room in a building, and the objects in the target space represent, for example, the walls and windows of the room.

[0042] FIG. 6 is a first flowchart illustrating the processing flow of the thermal environment analysis method according to this embodiment. The processing flow described below may be executed by, for example, an image processing device including a processor such as a CPU, a memory in which programs and data executed by the processor are expanded, a storage device, and the like. This image processing device loads a program stored in an auxiliary storage device into a working area of ​​a main storage device and executes it, thereby achieving various functions consistent with a predetermined purpose. However, some or all of the functions may be realized by hardware circuits such as an ASIC or FPGA. Furthermore, such an image processing device may be installed in the measurement device 1 described above in the first embodiment, or may be realized by an external server device.

[0043] In this flow, first, in S101, measurement data is acquired by multiple detectors included in the measurement device 1. Here, the measurement data is data related to infrared radiation from objects in the target space measured by the infrared sensor 2 described in the first embodiment, and data related to the distance to objects in the target space measured by the distance measuring sensor 3. In this embodiment, the measurement device 1 further includes a temperature sensor and a humidity sensor as detectors, and the temperature data and humidity data measured by these sensors are also acquired in the processing of S101. Note that the image processing device can acquire the above-mentioned measurement data, for example, via a sensor board when the image processing device is installed in the measurement device 1, or via a communication interface when the image processing device is implemented by an external server device.

[0044] Next, the image processing device generates three-dimensional point cloud information representing the positions of three-dimensional points in the target space based on the distances to objects in the target space measured by the distance sensor 3, and generates temperature information relating to the temperatures of objects in the target space based on the infrared radiation of the objects in the target space measured by the infrared sensor 2 (S102). Well-known techniques can be used to generate the three-dimensional point cloud information and temperature information. The three-dimensional point cloud information may be generated using a CAD model based on an image of the target space captured by a camera, or the CAD model may be created in advance.

[0045] After generating the three-dimensional point cloud information and temperature information in the process of S102, the image processing device then executes a process of mapping the temperature information onto a three-dimensional point cloud of the target space using the three-dimensional point cloud information (S103). At this time, the image processing device generates a three-dimensional temperature point cloud by combining a matrix of the temperature information with the three-dimensional point cloud. Then, it executes a process of visualizing the temperature information (three-dimensional temperature point cloud) mapped onto the three-dimensional point cloud of the target space in a three-dimensional model of the target space (S104). At this time, the image processing device generates a model as a three-dimensional color point cloud mapped to an arbitrary color spectrum. Note that these processes can be performed using well-known techniques.

[0046] This allows, for example, temperature information on the wall surfaces that define the target space to be visualized three-dimensionally in all directions. While conventional measurement devices can only obtain two-dimensional information within a certain measurement range using infrared sensors, the present disclosure makes it possible to automatically visualize the thermal environment of the target space in all directions.

[0047] The image processing device then evaluates the thermal insulation and airtightness of the target space based on the visualized temperature information (S105). After the process of S105, the execution of this flow ends.

[0048] In the evaluation of insulation and airtightness described above, areas of walls, windows, etc. separating the inside and outside of the target space that are lower or higher than the surrounding temperature contour may be evaluated as lacking insulation or airtightness.

[0049] In addition, in the thermal environment analysis method of this embodiment, the thermal insulation and airtightness of the target space may be evaluated based on changes in temperature information over time. Fig. 7 is a second flowchart illustrating the processing flow of the thermal environment analysis method according to this embodiment. Note that, in the processes shown in Fig. 7, the same reference numerals are used for processes that are substantially the same as those shown in Fig. 6, and detailed descriptions thereof will be omitted.

[0050] 7, in the process of S201, it is determined whether or not the measurement time has arrived. Here, the measurement time is a time that can be set at predetermined time intervals, for example, a time that is set every hour from an arbitrary initial time. If the determination in S201 is affirmative, the image processing device proceeds to the process of S101, and if the determination in S201 is negative, the image processing device proceeds to the process of S202.

[0051] If the determination in S201 is affirmative, the image processing device executes the processes of S101 to S103 shown in Fig. 6. That is, based on the measurement data measured by the sensor at a predetermined time interval, the temperature information is mapped onto a three-dimensional point cloud for each measurement time.

[0052] On the other hand, if the determination in S201 is negative, the image processing device then determines in S202 whether the measurement end time has arrived. Here, the measurement end time can be set arbitrarily, for example, 24 hours after the initial time. If the determination in S202 is positive, the image processing device proceeds to S203, and if the determination in S202 is negative, the image processing device returns to S201.

[0053] If a positive judgment is made in S202, the image processing device then performs a process of visualizing the temperature information (three-dimensional temperature point cloud) mapped to the three-dimensional point cloud of the target space for each measurement time over time in a three-dimensional model of the target space (S203).

[0054] The image processing device then evaluates the thermal insulation and airtightness of the target space based on the visualized temperature information (S204). After the process of S204, the execution of this flow ends.

[0055] In the evaluation of thermal insulation and airtightness described above, if the temperature change over time, which is the change over time in the temperature information visualized in the process of S203, is linked to the change in the outside air temperature outside the target space, the target space can be evaluated as having a lack of thermal insulation and / or airtightness. Specifically, if the temperature change over time is small compared to the change in the outside air temperature, it can be evaluated as having suppressed heat transfer inside and outside the target space, and if the temperature change over time is large in linkage with the change in the outside air temperature, it can be evaluated as having a lack of insulation, air leakage, or a thermal bridge in the walls, windows, etc. separating the inside and outside of the target space.

[0056] Furthermore, in the evaluation of thermal insulation and airtightness described above, if a temperature difference occurs in the vertical direction of the target space as a result of temperature changes over time, the target space may be evaluated as having a lack of thermal insulation and / or airtightness. Here, the present inventors have discovered that if the insulation or airtightness of the target space is insufficient, a temperature difference may occur in the vertical direction of the target space. Therefore, in this embodiment, if a temperature difference occurs in the vertical direction of the target space as a result of temperature changes over time, it may be evaluated that there is a lack of insulation, an air leak, or a thermal bridge in the walls, windows, etc. separating the inside and outside of the target space.

[0057] If the evaluation of the thermal insulation and airtightness indicates that the thermal insulation and / or airtightness of the target space is deficient, the image processing device may further evaluate the cause of the deficient thermal insulation and / or airtightness of the target space based on image diagnosis using machine learning of temperature changes over time. In the evaluation of the cause of the deficient thermal insulation and / or airtightness, image data of the temperature changes over time may be input to a machine learning model constructed by learning using predetermined training data, and an identification result may be output.

[0058] The machine learning model may be, for example, a neural network model generated by deep learning. FIG. 8 is a diagram illustrating a neural network constituting the machine learning model. The machine learning model 30 includes an input layer 31 that receives input image data of temperature changes over time, an intermediate layer (hidden layer) 32 that extracts, from the image data input to the input layer 31, feature quantities representing partial temperature changes due to defects in the thermal insulation and / or airtightness of the target space, and an output layer 33 that outputs an identification result (cause of defect) based on the feature quantities. In the example of FIG. 8 , the machine learning model 30 includes one intermediate layer 32, and the output of the input layer 31 is input to the intermediate layer 32, and the output of the intermediate layer 32 is input to the output layer 33. However, the number of intermediate layers 32 does not have to be limited to one, and the machine learning model 30 may include two or more intermediate layers 32.

[0059] 8, each of the layers 31 to 33 includes one or more neurons. For example, the number of neurons in the input layer 31 can be set according to the input image data. The number of neurons in the output layer 33 can be set according to the cause of the defect, which is the classification result.

[0060] Neurons in adjacent layers are then connected as appropriate, and weights (connection loads) are set for each connection based on the results of machine learning. In the example of Figure 8, each neuron is connected to all neurons in the adjacent layer, but the neuron connections are not limited to this example and can be set as appropriate.

[0061] Such a machine learning model 30 is constructed by performing supervised learning using training data that is a combination of explanatory variables, such as the magnitude of the difference between the ambient temperature and a location where temperature changes over time on a building wall or window, or a value obtained by differentiating this difference with the distance to the location of the temperature change, and labels that indicate causes of heat transfer, such as insulation defects, air leaks, and thermal bridges. Specifically, the combinations of features and labels are provided to a neural network, and the connection weights between neurons are tuned so that the output of the neural network is the same as the labels. In this way, the features of the training data are learned and a machine learning model for estimating results from inputs is inductively acquired.

[0062] In addition, in this embodiment, physical properties, including thermal properties, of objects in the target space may be estimated based on the temperature information visualized in the processing of S203 shown in Figure 7 above and the temperatures inside and outside the target space.

[0063] In this case, for example, by using the inside and outside temperature information and the heat conduction model for the wall surface of a building, it is possible to estimate the physical properties of the heat insulating material used on the wall surface.

[0064] According to the thermal environment analysis method described above, a technology that can automatically measure the thermal environment of a target space in all directions can be realized by relatively simple means.

[0065] <Modification of Second Embodiment> A thermal environment analysis method in a modification of the second embodiment will be described below. In this modification, in addition to the evaluation of the thermal insulation and airtightness of the target space described in the above description of the second embodiment, a vertical difference, which is the difference in thermal insulation in the vertical direction of the target space, and / or a left-right difference, which is the difference in thermal insulation in the left-right direction of the target space, are calculated. Then, a comfort evaluation is performed to evaluate the comfort of the user in the target space based on the above vertical difference and / or left-right difference.

[0066] Here, the above-mentioned vertical difference and horizontal difference can be calculated, for example, using the temperature difference between the ceiling surface and the floor surface (vertical difference) in a contour image representing the temperature of the wall surface of the target space, or the temperature difference between an arbitrary wall surface and the wall surface opposite that wall surface (horizontal difference).

[0067] The image processing device then calculates the above-mentioned vertical and horizontal differences, and based on the results, can evaluate that the comfort of the user in the target space is impaired if there is a difference of, for example, 2 degrees Celsius between these.

[0068] The image processing device may further calculate an operative temperature that affects the user based on an average radiation temperature, which is a radiation temperature from objects in the target space.

[0069] The average radiant temperature can be calculated by multiplying the surface temperature of each wall defining the target space by a coefficient corresponding to the positional relationship between the user and the wall, and then adding up the products for each wall. The sensible temperature can be calculated by taking a weighted average of the air temperature and the average radiant temperature in the target space.

[0070] Based on the operative temperature calculated in this manner, the image processing device can assess that the comfort of the user in the target space is impaired, for example, if there is a difference of 2°C between the air conditioning temperature set by the user in the target space and the above-mentioned operative temperature.

[0071] In this case, if the difference between the above-mentioned operative temperature and the air temperature of the target space is, for example, 2°C or more, the image processing device can evaluate that heat is being transferred inside and outside the target space due to a lack of insulation and / or airtightness of the target space.

[0072] <Other Modifications> The above-described embodiment is merely an example, and the present disclosure can be implemented with appropriate modifications within the scope that does not deviate from the gist thereof.

[0073] For example, air conditioning equipment that may be installed in a target space may be optimized based on the thermal environment of the target space analyzed using the measuring device 1 described in the first embodiment above.

[0074] In this case, based on the temperature information visualized by mapping it onto a three-dimensional point cloud of the target space, for example, air conditioning equipment can be placed in a position where the temperature distribution in the target space can be made more uniform by air conditioning.

[0075] Furthermore, the air conditioning capacity of an air conditioning system installed in a target space is often set based on the floor area of ​​the target space. However, if the target space has low insulation and / or airtightness, the air conditioning capacity that can be set based on the floor area of ​​the target space may be insufficient. Therefore, according to this modification, the air conditioning capacity of the air conditioning system installed in the target space can be set based on the floor area of ​​the target space and the insulation and / or airtightness of the target space.

[0076] DESCRIPTION OF SYMBOLS 1. Measuring device 2. Infrared sensor 3. Distance measurement sensor 4. Motor 5. Power supply 6. Electronic board 7. Sensor board 10. Housing 20. Rotating part 41. First motor 42. Second motor

Claims

1. A thermal environment measuring device that measures the thermal environment of a target space in all directions by rotating multiple detectors around multiple axes, comprising: a motor that rotates the multiple detectors around the multiple axes; a housing unit that houses the motor, a power supply, and an electronic board; and a rotating unit that is journaled on the housing unit and houses the multiple detectors and their corresponding sensor boards, wherein the multiple detectors include an infrared sensor that measures infrared radiation from an object in the target space, and a distance measuring sensor that measures the distance to the object by irradiating the object in the target space with laser light and receiving light reflected from the object, and wherein the housing unit is rotated around a predetermined first axis by a first motor that constitutes the motor, and the rotating unit is rotated around a second axis that is approximately perpendicular to the first axis by a second motor that constitutes the motor.

2. The thermal environment measuring device according to claim 1, wherein the infrared sensor and the distance measuring sensor are arranged substantially on the axis of the first axis and the second axis.

3. The thermal environment measuring device of claim 1, wherein the rotating part has shaft ends at both ends, the housing part has bearings for supporting the shaft ends of the rotating part, and the sensor board is configured to penetrate through the shaft ends from the rotating part side of the bearing to the housing part side, so that a part of the sensor board is built into the housing part.

4. A thermal environment analysis method using a thermal environment measuring device according to any one of claims 1 to 3, comprising: a first step of generating three-dimensional point cloud information representing the positions of three-dimensional points in the target space based on the distance to an object in the target space measured by the ranging sensor; a second step of mapping temperature information relating to the temperature of an object in the target space measured by the infrared sensor onto the three-dimensional point cloud of the target space using the three-dimensional point cloud information; and a third step of visualizing the temperature information mapped onto the three-dimensional point cloud of the target space.

5. A thermal environment analysis method as described in claim 4, further comprising a first evaluation step in which, in the second step, the temperature information measured by the infrared sensor at a predetermined time is mapped, and the thermal insulation and / or airtightness of the target space is evaluated based on the temperature information visualized in the third step.

6. A thermal environment analysis method as described in claim 5, further comprising a comfort evaluation step in which an up-down difference, which is the difference in insulation in the vertical direction of the target space, and / or a left-right difference, which is the difference in insulation in the horizontal direction of the target space, is calculated in the first evaluation step, and the method further comprises a comfort evaluation step in which the comfort of a user in the target space is evaluated based on the up-down difference and / or the left-right difference.

7. A thermal environment analysis method as described in claim 6, wherein in the comfort evaluation step, an operative temperature affecting the user is further calculated based on the average radiant temperature, which is the radiant temperature from objects in the target space, and the user's comfort is evaluated based on the operative temperature, and in the first evaluation step, if the difference between the operative temperature and the air temperature of the target space is equal to or greater than a predetermined threshold, it is evaluated that heat is moving inside and outside the target space due to a lack of insulation and / or airtightness of the target space.

8. A thermal environment analysis method as described in claim 4, further comprising: in the second step, the temperature information measured by the infrared sensor at predetermined time intervals is mapped for each measurement time; in the third step, the temperature information mapped for each measurement time is visualized over time; and a second evaluation step of evaluating the insulation and / or airtightness of the target space based on the temperature information visualized in the third step.

9. A thermal environment analysis method as described in claim 8, wherein in the second evaluation step, if the temperature change over time, which is the change over time of the temperature information visualized in the third step, is linked to the change in outside air temperature outside the target space, the target space is evaluated to have a lack of insulation and / or airtightness.

10. A thermal environment analysis method as described in claim 8, wherein in the second evaluation step, if a temperature difference occurs in the vertical direction of the target space in the temperature change over time, which is the change over time of the temperature information visualized in the third step, the target space is evaluated to have a lack of insulation and / or airtightness.

11. A thermal environment analysis method as described in claim 9 or claim 10, further comprising: if the second evaluation step evaluates that the insulation and / or airtightness of the target space is deficient, evaluating the cause of the deficient insulation and / or airtightness of the target space based on image diagnosis using machine learning of the temperature change over time; and in evaluating the cause of the deficientness, inputting image data of the temperature change over time into a machine learning model constructed by learning using predetermined training data, and outputting an identification result.

12. A thermal environment analysis method as described in claim 4, further comprising: in the second step, the temperature information measured by the infrared sensor at predetermined time intervals is mapped for each measurement time; in the third step, the temperature information mapped for each measurement time is visualized over time; and an estimation step of estimating physical characteristics, including thermal properties, of objects in the target space based on the temperature information visualized in the third step and the temperatures inside and outside the target space.

Images