Ventilation system, learning device, and inference device

Abstract

The present disclosure relates to a ventilation system for maintaining an air environment in a parking place by supplying the air from the outside and exhausting the air to the outside. The ventilation system includes an air supply blower for supplying the external air from an air supply port to a parking place, an air exhaust blower for exhausting the air in the parking place to the outside from an air exhaust port, a conveyance blower for conveying an air flow from the air supply blower to the air exhaust blower, an imaging unit for imaging the inside of the parking place and outputting image data, and a control unit for detecting a movement of a vehicle on the basis of the image data output from the imaging unit and changing an air volume of the conveyance blower.

Description

Ventilation system, learning device and inference device

[0001] The present disclosure relates to a ventilation system, a learning device, and an inference device.

[0002] In underground or indoor parking lots, ventilation using duct piping does not provide sufficient ventilation in the center or complicated areas of the parking lot, and air containing exhaust gases may stagnate there. Therefore, ductless ventilation systems equipped with a conveying fan that conveys air from an intake fan to an exhaust fan are often used. Patent Document 1 discloses a ventilation system that includes a CO sensor installed near the exhaust fan and outputting a signal indicating the CO gas concentration in the surrounding area, and an airflow control device that controls the operation of at least one of the intake fan, exhaust fan, and conveying fan based on the output of the CO sensor. The ventilation system combines multiple conveying fans to connect their airflows and generate an airflow from the intake fan to the exhaust fan.

[0003] Patent No. 6807373

[0004] If a CO sensor is installed near the exhaust fan, there will be a time lag before exhaust gases generated in the parking lot reach the CO sensor near the exhaust fan. Therefore, controlling the fan based on the output of the CO sensor will not quickly exhaust exhaust gases. Therefore, the present disclosure aims to provide a ventilation system that can quickly exhaust exhaust gases in parking lots.

[0005] A ventilation system according to the present disclosure includes an intake fan that supplies outside air to a parking lot through an intake port, an exhaust fan that exhausts the parking lot air to the outside through an exhaust port, and a transport fan that transports airflow from the intake fan to the exhaust fan. The ventilation system further includes an imaging unit that captures images of the interior of the parking lot and outputs image data, and a control unit that detects vehicle movement based on the image data output from the imaging unit and adjusts the air volume of the transport fan.

[0006] According to the ventilation system of the present disclosure, vehicle movement is detected based on image data output from the imaging unit and the air volume of the conveying blower is changed, so exhaust gases can be quickly discharged within the parking lot.

[0007] 11 is a schematic diagram showing the ventilation system 100 according to embodiment 1, installed in a parking lot.

[0023] FIG. 12 is a schematic diagram showing signal communication connections in the ventilation system 100.

[0024] FIG. 13 is a block diagram showing the functional configuration of the control unit 30 of the ventilation system 100.

[0025] FIG. 14 is a block diagram showing the hardware configuration of the control unit 30 of the ventilation system 100.

[0026] FIG. 15 is a flowchart showing the operation of the control unit 30 of the ventilation system 100.

[0027] FIG. 16 is a schematic diagram showing a plurality of areas set in a parking lot in which the ventilation system 100 is installed.

[0028] FIG. 17 is a flowchart showing the operation of step S4 shown in FIG. 5.

[0029] FIG. 18 is a schematic diagram showing the ventilation system 110 according to embodiment 2, installed in a parking lot.

[0030] FIG. 19 is a schematic diagram showing the system of airflow generated by the ventilation system 110 of FIG. 8.

[0031] FIG. 19 is a schematic diagram showing another example of the arrangement of the ventilation system 110 in a parking lot.

[0032] FIG. 19 is another schematic diagram showing the system of airflow generated by the ventilation system 110 of FIG. 10.

[0033] FIG. 20 is a schematic diagram showing the ventilation system 120 according to embodiment 3, installed in a parking lot. FIG. 1 is a schematic diagram showing a ventilation system 130 according to a fourth embodiment, the ventilation system 130 being installed in a parking lot. FIG. 2 is a block diagram showing a configuration of a learning device 200 according to the fourth embodiment. FIG. 3 is a flowchart showing the operation of the learning device 200. FIG. 4 is a block diagram showing a configuration of an inference device 300 according to the fourth embodiment. FIG. 5 is a flowchart showing the operation of the inference device 300 and the operation of the ventilation system 130.

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the drawings and the following description, identical or substantially identical components are designated by the same reference numerals, and descriptions of components designated by the same reference numerals will not be repeated.

[0009] Embodiment 1. FIG. 1 is a schematic diagram showing a ventilation system 100 according to embodiment 1 of the present disclosure. The ventilation system 100 is installed in an airtight parking lot, such as an underground parking lot or an indoor parking lot, and ventilates the parking lot and expels exhaust gases outside. The ventilation system 100 includes an intake fan 5, an exhaust fan 6, and multiple transport fans 90. The parking lot has a generally rectangular planar shape, with an intake vent 1 and an exhaust vent 2 located at diagonal corners of the parking lot. The intake fan 1 and the intake fan 5 are located near the entrance 8, and the intake fan 5 supplies outside air into the parking lot through the intake fan 1. The exhaust fan 2 and the exhaust fan 6 are located at a corner near the exit 9, and the exhaust fan 6 expels air from the parking lot to the outside through the exhaust fan 2. The multiple transport fans 90 are installed in the parking lot and transport air from the intake fan 5 to the exhaust fan 6 to promote ventilation within the parking lot.

[0010] The figure illustrates a parking lot having parking spaces 7 for 26 vehicles and a vehicle movement path 10 that branches into two near an entrance 8 and meets near an exit 9. One of the two branching vehicle movement paths 10 is referred to as vehicle movement path 10-1, and the other is referred to as vehicle movement path 10-2. Of the multiple conveying fans 90, conveying fans 90-1 and 90-3 are installed along vehicle movement path 10-1, and conveying fans 90-2 and 90-4 are installed along vehicle movement path 10-2. Conveying fans 90-1 and 90-2 are installed close to each other, and conveying fans 90-3 and 90-4 are installed at diagonal corners of the parking lot.

[0011] The conveying blowers 90-1 and 90-3 generate airflows 12-1 and 12-3, respectively. The conveying blower 90-1 is installed upwind of the conveying blower 90-3, which is located in a position where the airflow 12-1 reaches. Therefore, the conveying blowers 90-1 and 90-3 form an airflow that flows from the air intake 1 to the exhaust 2 via the vehicle travel path 10-1. The conveying blowers 90-2 and 90-4 generate airflows 12-2 and 12-4, respectively. The conveying blower 90-2 is installed upwind of the conveying blower 90-4, which is located in a position where the airflow 12-2 reaches. Therefore, the conveying blowers 90-2 and 90-4 form an airflow that flows from the air intake 1 to the exhaust 2 via the vehicle travel path 10-2. In the following description, unless otherwise specified, the conveying blower 90 refers to each of the conveying blowers 90-1 to 90-4.

[0012] The ventilation system 100 includes an imaging unit 20. The imaging unit 20 is installed in a parking lot, captures images of the interior of the parking lot, and outputs the image data. The imaging unit 20 is disposed in a position where it can capture images of at least the vehicle movement paths 10-1 and 10-2. Specifically, the imaging unit 20 has two cameras 20-1 and 20-2. The cameras 20-1 and 20-2 are installed near the conveying blowers 90-3 and 90-4, respectively, and are disposed at diagonal positions in the parking lot. The cameras 20-1 and 20-2 output image data of images captured in the directions they are facing.

[0013] The ventilation system 100 includes a control unit 30. While there are no restrictions on the installation location, the control unit 30 is installed, for example, adjacent to the conveying blower 90-2. FIG. 2 is a schematic diagram showing the signal communication connections in the ventilation system 100. The control unit 30 is connected to each of the intake air blower 5, exhaust air blower 6, conveying blowers 90-1 to 90-4, and cameras 20-1 and 20-2 by wire or wirelessly. To simplify wiring installation, it is desirable that the control unit 30, intake air blower 5, exhaust air blower 6, conveying blowers 90-1 to 90-4, and cameras 20-1 and 20-2 are each wirelessly connected to the network 140. Note that since the control unit 30 is adjacent to the conveying blower 90-2, it may be connected to the conveying blower 90-2 by wire. The control unit 30 may also be provided inside the conveying blower 90-2.

[0014] The control unit 30 controls the operation of the air supply blower 5, the exhaust blower 6, and the conveying blower 90. With regard to the control of the conveying blower 90, the control unit 30 detects the movement of the vehicle based on image data output from the imaging unit 20, and changes the air volume of at least one of the conveying blowers 90-1 to 90-4. The air volume of a blower is the amount of airflow generated by the blower.

[0015] 3 is a block diagram showing the functional configuration of the control unit 30. The control unit 30 includes a vehicle movement detection unit 31, a vehicle shape detection unit 32, and a blower control unit 33. The vehicle movement detection unit 31 detects the movement of a vehicle based on image data received from the imaging unit 20. The vehicle movement detection unit 31 also detects the position of a moving vehicle and outputs vehicle position information indicating the position of the vehicle. The vehicle shape detection unit 32 detects the shape of the moving vehicle based on the image data received from the imaging unit 20. The vehicle shape detection unit 32 outputs vehicle shape information indicating the size of the vehicle.

[0016] When the vehicle movement detection unit 31 detects the movement of the vehicle, the blower control unit 33 identifies at least one of the conveyance blowers 90-1 to 90-4 based on the vehicle position information output from the vehicle movement detection unit 31. The blower control unit 33 also determines the air volume of the identified conveyance blower based on the vehicle shape information.

[0017] The blower control unit 33 transmits an air volume control command to the identified conveyance blower. The air volume control command includes air volume information specifying the air volume determined based on the vehicle shape information. The conveyance blower that has received the air volume control command changes the air volume to the specified air volume based on the air volume information and operates.

[0018] The blower has a motor and a fan, and generates airflow by rotating the fan with the motor. The air volume of the blower changes by changing the operating parameters of the blower (such as the motor's rotation speed, the power or power frequency supplied to the motor, etc.). Therefore, the air volume information is information for setting the operating parameters of the blower. In the case of a blower in which the air volume can be set in multiple stages, the air volume information may be information specifying an operating mode indicating one of the multiple settable stages. Furthermore, the air volume information may be information indicating the difference between the air volume before and after the change.

[0019] Fig. 4 is a block diagram showing the hardware configuration of the control unit 30. As shown in Fig. 4(a), the control unit 30 is composed of a processor 70, a memory 71, and a bus 72. The processor 70 performs processing according to a program to realize the functions of the vehicle movement detection unit 31, the vehicle shape detection unit 32, and the blower control unit 33. The program is stored in the memory 71 and provided to the processor 70 via the bus 72. The processor 70 is, for example, a central processing unit (CPU), and the memory 71 is a storage device including a volatile memory such as a RAM (Random Access Memory), and a non-volatile memory such as a ROM (Read Only Memory) or a flash memory.

[0020] Image data from the imaging unit 20 is received by an interface circuit (not shown) and stored in memory 71 via a bus 72. The processor 70 reads the image data from the memory 71 and processes it. An air volume control command generated by the processor 70 is sent via the bus 72 to another interface circuit (not shown) and then to the conveyance control unit.

[0021] The configuration having a processor 70 and a memory 71 as shown in Fig. 4(a) is realized by a microcomputer or the like that can also be used to control other electrical or electronic devices. However, the present invention is not limited to this, and the control unit 30 can also be realized by a dedicated processing circuit 73 as shown in Fig. 4(b).

[0022] In the ventilation system 100, the control unit 30 increases the air volume of one or more conveyance blowers when it detects vehicle movement from image data. Figure 5 is a flowchart showing the operation of the control unit 30 for performing this control. The start is the point at which operation of the ventilation system 100 begins after installation in the parking lot, and the control unit 30 instructs the intake air blower 5, exhaust air blower 6, and conveyance blower 90 to operate so that each blows air at a predetermined air volume. The conveyance blower 90 is controlled to operate at the minimum air volume within the settable air volume range, for example.

[0023] In step S1, the vehicle movement detection unit 31 and the vehicle shape detection unit 32 each acquire image data from the imaging unit 20, i.e., from both cameras 20-1 and 20-2. In step S2, the vehicle movement detection unit 31 detects the movement of the vehicle by detecting a change in the position of the vehicle in the moving image based on the image data. If there is no moving vehicle in the image data (No), the operation flow returns to step S1. If there is a moving vehicle (Yes), in step S3, the vehicle movement detection unit 31 detects the position of the moving vehicle.

[0024] FIG. 6 is a schematic diagram showing multiple areas set in the parking lot shown in FIG. 1. Four areas A-1 to A-4 are set on the vehicle movement path 10. Areas A-1 and A-3 are set on the vehicle movement path 10-1, and area A-1 is located upwind of area A-3 in the air currents generated by the conveying fans 90-1 and 90-3. Areas A-1 and A-3 correspond to the conveying fans 90-1 and 90-3, respectively. Areas A-2 and A-4 are set on the vehicle movement path 10-2, and area A-2 is located upwind of area A-4 in the air currents generated by the conveying fans 90-2 and 90-4. Areas A-2 and A-4 correspond to the conveying fans 90-2 and 90-4, respectively.

[0025] As one mode of detecting the position of the vehicle, the vehicle movement detection unit 31 detects from the image data which of areas A-1 to A-4 the vehicle is moving through. The movement of the vehicle in areas A-1 and A-3 is determined from the image data of camera 20-1, and the movement of the vehicle in areas A-2 and A-4 is determined from the image data of camera 20-2. The vehicle movement detection unit 31 generates vehicle position information indicating the area through which the vehicle is moving as the position of the vehicle. The movement of the vehicle and the area through which the vehicle is moving are detected from the image data using known image recognition technology. The image data may be a moving image with a frame rate low enough that the movement of the vehicle can be detected.

[0026] Next, in step S4, the blower control unit 33, based on the vehicle position information output from the vehicle movement detection unit 31, identifies the conveyance blower among the conveyance blowers 90-1 to 90-4 whose air volume should be increased.

[0027] FIG. 7 is a flowchart showing the operation of step S4 in more detail. In step S4-1, the blower control unit 33 determines whether a vehicle is present in area A-1. If a vehicle is present in area A-1, exhaust gases tend to accumulate in area A-1, so it is necessary to increase the airflow in area A-1. Furthermore, to promote exhaust outside the parking lot, it is desirable to increase the airflow not only in area A-1 but also in area A-3, which is downstream of area A-1. Therefore, if it is determined that a vehicle is present in area A-1 (Yes), in step S4-2, the blower control unit 33 identifies the conveying blowers 90-1 and 90-3. Step S4-2 is performed regardless of whether other vehicles are present in area A-3. The operation flow then proceeds to step S4-5.

[0028] If it is determined in step S4-1 that no vehicle is present (No), then in step S4-3 the blower control unit 33 determines whether or not a vehicle is present in area A-3. If it is determined that a vehicle is present (Yes), then in step S4-4 the blower control unit 33 identifies the conveying blower 90-3. At this time, since there is no need to increase the air volume in area A-1, the conveying blower 90-1 is not identified. Thereafter, the operation flow proceeds to step S4-5. Furthermore, if it is determined in step S4-3 that no vehicle is present (No), then the operation flow also proceeds to step S4-5.

[0029] In step S4-5, the blower control unit 33 determines whether a vehicle is present in area A-2. If a vehicle is present in area A-2, exhaust gases are likely to accumulate in area A-2, so it is necessary to increase the airflow in area A-2. Furthermore, to promote exhaust outside the parking lot, it is desirable to increase the airflow not only in area A-2 but also in area A-4, which is downstream of area A-2. Therefore, if it is determined that a vehicle is present in area A-2 (Yes), in step S4-6, the blower control unit 33 identifies the conveying blowers 90-2 and 90-4. Step S4-6 is performed regardless of whether another vehicle is present in area A-4. The operational flow then proceeds to step S5.

[0030] If it is determined in step S4-5 that no vehicle is present (No), then in step S4-7 the blower control unit 33 determines whether or not a vehicle is present in area A-4. If it is determined that a vehicle is present (Yes), then in step S4-8 the blower control unit 33 identifies the conveying blower 90-4. At this time, since there is no need to increase the air volume in area A-2, the conveying blower 90-2 is not identified. Thereafter, the operation flow proceeds to step S5. Also, if it is determined in step S4-7 that no vehicle is present (No), the operation flow proceeds to step S5.

[0031] Returning to FIG. 5 , in step S5, the vehicle shape detection unit 32 determines the size of each vehicle present in areas A-1 to A-4. The vehicle shape detection unit 32 detects the vehicle shape using existing image recognition technology and determines the vehicle size from the detected shape. In step S6, the blower control unit 33 receives information regarding the vehicle size from the vehicle shape detection unit 32 and determines the air volume of the conveyance blower identified in step S4 based on the vehicle size. The determined air volume is greater than the air volume of the conveyance blowers 90-1 to 90-4 at the start of operation of the ventilation system 100. Because larger vehicles emit larger amounts of exhaust gas, it is desirable to increase the air volume of the conveyance blower for larger vehicles. For example, the blower control unit 33 is set with multiple thresholds related to vehicle size, and the blower control unit 33 determines the air volume so that the air volume increases each time the determined vehicle size exceeds a threshold.

[0032] In step S7, the blower control unit 33 sends an air volume control command to the conveyance blower identified in step S4, and controls the conveyance blower to change the air volume to the one determined in step S6. The conveyance blower that received the air volume control command changes the air volume based on the air volume control command. If the vehicle is in area A-1, conveyance blowers 90-1 and 90-3 receive the air volume control command. If the vehicle is in area A-2, conveyance blowers 90-2 and 90-4 receive the air volume control command. If the vehicle is in area A-3, conveyance blower 90-3 receives the air volume control command. If the vehicle is in area A-4, conveyance blower 90-4 receives the air volume control command. In either case, the conveyance blower that received the air volume control command increases its air volume.

[0033] When multiple vehicles are present in the same area, the fan control unit 33 may control the air volume of the transport fan corresponding to that area to be the largest of the air volumes determined for the multiple vehicles. Alternatively, the fan control unit 33 may control the air volume of the transport fan to be the largest air volume determined for the multiple vehicles, and may further increase the air volume in accordance with the number of vehicles from the largest air volume.

[0034] In step S8, the blower control unit 33 determines whether a predetermined time has elapsed since the air volume of the conveyance blower was changed in step S7. After the air volume has been changed, the conveyance blower continues to operate at the air volume changed in step S7 until the predetermined time has elapsed (No). If the predetermined time has elapsed after the air volume has been changed (Yes), in step S9, the blower control unit 33 controls the air volume of the conveyance blower so as to return it to the air volume before the change, i.e., the air volume at the start of operation of the ventilation system 100. The conveyance blower receives an air volume control command from the blower control unit 33 and returns the air volume to its original value based on the air volume control command. The operation flow then returns to step S1, and the control unit 30 repeats the operations of steps S1 to S9. Note that each of steps S1 to S9 can be rephrased as an operation performed by the control unit 30.

[0035] As described above, in the ventilation system 100 according to this embodiment, the control unit 30 detects the movement of a vehicle based on image data and changes the air volume of at least one conveyance blower. By using image data, the control unit 30 can quickly detect that the vehicle is generating exhaust gas, and can quickly discharge the exhaust gas.

[0036] Furthermore, with the ventilation system 100, the control unit 30 detects the position of a moving vehicle from image data, identifies at least one of the multiple conveyance blowers 90-1 to 90-4 based on the detected position, and increases the airflow of the identified conveyance blower. In areas where exhaust gas is not generated in large quantities, it is not necessary to increase the airflow of the conveyance blower. In other words, excessive ventilation can be suppressed, thereby saving power consumption. This leads to reduced running costs for the ventilation system 100.

[0037] The control unit 30 identifies the conveying fan that generates an airflow at the detected position of the vehicle as the conveying fan that increases the air volume, so that it is possible to quickly identify the location in the parking lot where exhaust gas needs to be exhausted. The control unit 30 also identifies the conveying fan further downstream as a conveying fan that increases the air volume, so that exhaust gas can be efficiently guided outside the parking lot.

[0038] Since the imaging unit 20 that captures images is cheaper than a CO sensor that detects CO concentration, controlling the air volume of the conveying blower based on image data also contributes to reducing the initial cost of the ventilation system 100.

[0039] Below, several variations of the first embodiment will be described.

[0040] Variation (1): In step S2, the vehicle movement detection unit 31 detected a change in the position of the vehicle in the moving image. However, the vehicle movement may also be detected by detecting the vehicle's position. If a vehicle is present in any of areas A-1 to A-4 set on the vehicle movement path 10, the vehicle can be considered to be moving on the vehicle movement path 10. Therefore, in step S2, the vehicle movement detection unit 31 determines from the image data whether the vehicle is present in any of areas A-1 to A-4. If it is determined that the vehicle is present in any of areas A-1 to A-4, the vehicle movement detection unit 31 is deemed to have detected the movement of the vehicle. Then, in step S3, the vehicle movement detection unit 31 generates vehicle position information indicating the area (any of areas A-1 to A-4) in which the vehicle is present. On the other hand, if the vehicle is not present in the image, or if the vehicle is present but not in any of areas A-1 to A-4, it is determined that there is no moving vehicle, and the vehicle movement detection unit 31 returns to step S1. The image data used to detect the vehicle movement at this time may be a still image.

[0041] Modification (2): Step S4 is performed by the blower control unit 33, but may also be performed by the vehicle movement detection unit 31. At this time, the blower control unit 33 receives information identifying the conveyance blower from the vehicle movement detection unit 31 and transmits an air volume control command to the identified conveyance blower. Also, step S6 is performed by the blower control unit 33, but may also be performed by the vehicle shape detection unit 32. At this time, the blower control unit 33 includes the air volume determined by the vehicle movement detection unit 31 as air volume information in the air volume control command.

[0042] Modification (3): The control unit 30 does not necessarily require the vehicle shape detection unit 32. The blower control unit 33 can also control the conveyance blower to increase the air volume by a predetermined amount regardless of the size of the vehicle. This can reduce the processing load on the control unit 30.

[0043] Variation (4): The number and installation locations of the conveying blowers are changed depending on the size of the parking lot. Depending on the parking lot, it may be possible to install only one conveying blower. In this case, when the control unit 30 detects vehicle movement, step S4 for identifying the conveying blower is not necessary, and it is sufficient to increase the air volume of the only conveying blower. The number of cameras is also changed depending on the size of the parking lot. If the size of the parking lot is small, one camera may be sufficient as the imaging unit 20.

[0044] Embodiment 2. Figure 8 is a schematic diagram of a ventilation system 110 according to embodiment 2. The ventilation system 110 includes an intake air blower 5, an exhaust air blower 6, conveyance air blowers 90-1 to 90-4, cameras 20-1 and 20-2, and a control unit 30. The difference from embodiment 1 is the method for identifying the conveyance air blowers in the control unit 30; otherwise, the configuration and operation are the same as those of embodiment 1.

[0045] The control unit 30 has a parking lot map of the parking lot where the ventilation system 110 is installed. The parking lot map is stored in advance in the memory of the control unit 30. In the parking lot map, for example, two-dimensional coordinates are set on the plane of the parking lot, and the positions of the conveying fans 90-1 to 90-4, the cameras 20-1 and 20-2, and the exhaust port 2 are stored in advance in the control unit 30 in the form of two-dimensional coordinates.

[0046] As shown in Figure 9, the air supplied from the intake fan 5 is roughly divided into two systems: an airflow from the conveying fan 90-1 via the conveying fan 90-3 toward the exhaust fan 6, and an airflow from the conveying fan 90-2 via the conveying fan 90-4 toward the exhaust fan 6.

[0047] The straight line connecting the conveying blower 90-1 and the conveying blower 90-3 is defined as air path 91A, and corresponds to the conveying blower 90-1. Air path 91A is set using the coordinates of two points, the conveying blower 90-1 and the conveying blower 90-3. The straight line connecting the conveying blower 90-3 and the exhaust port 2 is defined as air path 91C, and corresponds to the conveying blower 90-3. Air path 91C is set using the coordinates of two points, the conveying blower 90-3 and the exhaust port 2. The straight line connecting the conveying blower 90-2 and the conveying blower 90-4 is defined as air path 91B, and corresponds to the conveying blower 90-2. Air path 91B is set using the coordinates of two points, the conveying blower 90-2 and the conveying blower 90-4. The straight line connecting the conveying fan 90-4 and the exhaust port 2 is defined as an air passage 91D, and corresponds to the conveying fan 90-4. The air passage 91D is set by the coordinates of two points, the conveying fan 90-4 and the exhaust port 2.

[0048] The parking lot map also contains information indicating the direction of the airflow in the air passages 91A to 91D. Therefore, the control unit 30 can determine from the parking lot map that the conveying blower 90-1 is located upstream of the conveying blower 90-3, and that the conveying blower 90-2 is located upstream of the conveying blower 90-4.

[0049] When a vehicle 11 is present in the parking lot, the vehicle movement detection unit 31 detects the position of the vehicle 11 as two-dimensional coordinates based on image data acquired from the cameras 20-1 and 20-2. The vehicle movement detection unit 31 outputs the detected position of the vehicle 11 as vehicle position information. This position detection by the vehicle movement detection unit 31 corresponds to step S3 in FIG. 5.

[0050] Here, the shortest distance from vehicle 11 to air duct 91A is defined as air duct distance 92A. The shortest distance from vehicle 11 to air duct 91B is defined as air duct distance 92B. The shortest distance from vehicle 11 to air duct 91C is defined as air duct distance 92C. The shortest distance from vehicle 11 to air duct 91D is defined as air duct distance 92D. The blower control unit 33 calculates each of air duct distances 92A to 92D based on the vehicle position information received from the vehicle movement detection unit 31. The blower control unit 33 identifies the air duct among air ducts 91A to 91D with the shortest air duct distance calculated by the vehicle movement detection unit 31, and identifies the conveying blower corresponding to the identified air duct. If there is a conveying blower downstream of the conveying blower, the blower control unit 33 also identifies that conveying blower. This identification of the conveying blower by the blower control unit 33 corresponds to step S4 in FIG. 5.

[0051] To facilitate understanding of the airflow path distances, FIG. 8 shows the airflow path distances 92A-92D when the vehicle 11 is parked in the parking space 7. However, because step S3 is performed after step S2, the airflow path distances 92A-92D are not calculated when the vehicle 11 is parked. However, step S3 may be performed before step S2. That is, the vehicle movement detection unit 31 detects the position of the vehicle 11 and calculates the airflow path distances 92A-92D, and then detects the movement of the vehicle 11. When the movement of the vehicle 11 is detected, in step S4, the blower control unit 33 identifies the transport blower based on the airflow path distances 92A-92D relative to the vehicle 11. The operation of the ventilation system 110 from this point onward is the same as step S5 in the first embodiment, and therefore a description thereof will be omitted.

[0052] In this way, the ventilation system 110 is characterized in that multiple air paths are set for each of the airflows generated by the conveying blowers 90-1 to 90-4, and the control unit 30 identifies the conveying blower corresponding to the air path closest to the vehicle as the one whose air volume should be increased.

[0053] Below, some modifications of the second embodiment will be described.

[0054] Variation (1): As in Variation (1) of Embodiment 1, the control unit 30 may detect vehicle movement based on the vehicle's position. For example, if the vehicle is not present in any parking space 7, it can be assumed that the vehicle is moving along the vehicle movement path 10. Therefore, it is assumed that the parking lot map contains information about the areas of all parking spaces 7. In step S3, the vehicle movement detection unit 31 detects the vehicle's position regardless of the vehicle's movement and generates vehicle position information as two-dimensional coordinates. Then, the vehicle movement detection unit 31 determines whether the detected vehicle's position is included in a parking space 7. If it determines that the vehicle is included in any parking space 7, the vehicle is not moving, and the vehicle movement detection unit 31 returns to step S1. If it determines that the vehicle's position is not included in any parking space 7, the vehicle 11 is considered to be a moving vehicle, and the vehicle movement detection unit 31 proceeds to step S4. Vehicle movement detection is performed in step S3, and step S2 is unnecessary.

[0055] Variation (2): The ventilation system 110 is not limited to the case where the air inlet 1 and the air outlet 2 are arranged diagonally as shown in FIG. 8 . The ventilation system 110 may be arranged at two adjacent corners of the four corners of the planar shape of the parking lot, for example, as shown in FIG. 10 , where the air inlet 1 is arranged at the upper corner on the left side and the air outlet 2 is arranged at the lower corner on the left side. In this case, the conveying blower 90-1 is installed near the conveying blower 90-3 and blows air toward the conveying blower 90-2. Therefore, as shown in FIG. 11 , the air supplied from the air supply blower 5 is roughly divided into two systems: an airflow from the conveying blower 90-3 toward the exhaust blower 6, and an airflow from the conveying blower 90-1 toward the exhaust blower 6 via the conveying blowers 90-2 and 90-4.

[0056] Modification (3): Each of the modifications (2) to (4) of the first embodiment also applies to the ventilation system 110 of the second embodiment.

[0057] Embodiment 3. Figure 12 is a schematic diagram of a ventilation system 120 according to embodiment 3. The ventilation system 120 includes an intake air blower 5, an exhaust air blower 6, conveyance air blowers 90-1 to 90-4, cameras 20-1 and 20-2, and a control unit 30. The difference from embodiment 1 is the method for identifying the conveyance air blowers in the control unit 30; otherwise, the configuration and operation are the same as those of embodiment 1.

[0058] The installation locations of the intake air blower 5, exhaust air blower 6, transport air blowers 90-1 to 90-4, cameras 20-1, 20-2, and control unit 30 are the same as in Figure 8. When viewing the parking lot from above, the upper right corner of Figure 12 is referred to as corner A, the upper left corner as corner B, the lower right corner as corner C, and the lower left corner as corner D. The air intake port 1 and intake air blower 5 are located near corner A. The transport air blowers 90-1 and 90-2 are located in the passage near corner A. The transport air blower 90-1 blows air toward corner B. The transport air blower 90-2 blows air toward corner C. The transport air blower 90-3 is located in the passage near corner B and blows air toward corner D. The transport air blower 90-3 is located in the passage near corner C and blows air toward corner D. An exhaust port 2 and an exhaust fan 6 are arranged near the corner D.

[0059] Camera 20-1 is placed near corner B, and camera 20-2 is placed near corner C. Therefore, the left side of the image captured by camera 20-1 becomes the right side of the image captured by camera 20-2, and the right side of the image captured by camera 20-1 becomes the left side of the image captured by camera 20-2. Cameras 20-1 and 20-2 have the same resolution.

[0060] A line 94A connecting camera 20-1 and camera 20-2 is an imaginary line added for convenience. A line 94B that passes through the midpoint between camera 20-1 and camera 20-2, is parallel to the floor of the parking lot, and is perpendicular to line 94A. The area tangent to lines 94A and 94B, and on the left side of line 94B as seen from camera 20-1, is referred to as area 93A. The area tangent to lines 94A and 94B, and on the right side of line 94B as seen from camera 20-1, is referred to as area 93C. The area tangent to lines 94A and 94B, and on the right side of line 94B as seen from camera 20-2, is referred to as area 93B. The area tangent to the lines 94A and 94B, which is on the left side of the line 94B as viewed from the camera 20-2, is referred to as area 93D. For convenience of illustration, areas 93A to 93D are shown apart from the lines 94A and 94B, but as described above, they are areas tangent to the lines 94A and 94B.

[0061] The vehicle movement detection unit 31 detects one of areas 93A to 93D as the position of the vehicle. The vehicle movement detection unit 31 first detects the position of the vehicle in the image captured by one of cameras 20-1 and 20-2. The position of the vehicle in the image is detected as left / right information indicating whether the vehicle is present in the right half or left half of the image. Assume that one of the cameras is camera 20-2, for example. If the vehicle is present in the right half of the image captured by camera 20-2, it is determined that the vehicle is present in either area 93A or 93B to the right of straight line 94A. If the vehicle is present in the left half of the image captured by camera 20-2, it is determined that the vehicle is present in either area 93C or 93D to the left of straight line 94A.

[0062] A vehicle in the image captured by camera 20-2 is also captured by the other camera, 20-1. Therefore, vehicle movement detection unit 31 compares the sizes of the vehicles captured by cameras 20-1 and 20-2. If the vehicle captured by camera 20-1 is larger, it can be determined that the vehicle is located on the side closer to camera 20-1 than straight line 94A. On the other hand, if the vehicle captured by camera 20-2 is larger, it can be determined that the vehicle is located on the side closer to camera 20-2 than straight line 94A.

[0063] Therefore, when the vehicle movement detection unit 31 detects that the vehicle imaged by camera 20-2 is on the right side of straight line 94A and that camera 20-1 appears larger than camera 20-2, it detects that the vehicle is in area 93A. When the vehicle movement detection unit 31 detects that the vehicle imaged by camera 20-2 is on the left side of straight line 94A and that camera 20-1 appears larger than camera 20-2, it detects that the vehicle is in area 93C. When the vehicle movement detection unit 31 detects that the vehicle imaged by camera 20-2 is on the right side of straight line 94A and that camera 20-2 appears larger than camera 20-1, it detects that the vehicle is in area 93B. When the vehicle movement detection unit 31 detects that the vehicle imaged by camera 20-2 is on the left side of straight line 94A and that camera 20-2 appears larger than camera 20-1, it detects that the vehicle is in area 93D. The vehicle movement detection unit 31 outputs the detected area as vehicle position information. This detection of the area by the vehicle movement detection unit 31 corresponds to step S3 in FIG.

[0064] In step S4, the blower control unit 33 identifies the conveyance blower whose air volume should be increased based on the vehicle position information output from the vehicle movement detection unit 31. If the vehicle position information indicates area 93A, the blower control unit 33 identifies the conveyance blower 90-1 that generates an airflow in area 93A and the conveyance blower 90-3 downstream thereof. If the vehicle position information indicates area 93C, the blower control unit 33 identifies the conveyance blower 90-3 that generates an airflow in area 93C. If the vehicle position information indicates area 93B, the blower control unit 33 identifies the conveyance blower 90-2 that generates an airflow in area 93B and the conveyance blower 90-4 downstream thereof. If the vehicle position information indicates area 93D, the blower control unit 33 identifies the conveyance blower 90-4 that generates an airflow in area 93D. This identification of conveyance blowers by the blower control unit 33 corresponds to step S4 in FIG. 5 . The subsequent operation of the ventilation system 120 is the same as step S5 in the first embodiment, and therefore a description thereof will be omitted.

[0065] As described above, the ventilation system 120 is characterized by comparing the sizes of vehicles captured by the two cameras 20-1 and 20-2, and identifying the vehicle as a transport fan for which the air volume should be increased based on the results of the comparison.

[0066] The modifications (2) to (4) of the first embodiment and the modification (2) of the second embodiment also apply to the ventilation system 120 of the third embodiment.

[0067] Fourth Embodiment A learning device 200 and an inference device 300 according to a fourth embodiment will be described. Both the learning device 200 and the inference device 300 are devices for learning and inference related to a ventilation system having a conveyance blower. The learning device 200 acquires learning data, determines a control method for the conveyance blower from the learning data using machine learning, and generates a trained model. The inference device 300 infers control information for controlling the conveyance blower from input data based on the trained model.

[0068] Since parking lots come in a variety of shapes and have different layouts of parking spaces 7 within them, it is preferable for efficient ventilation to control the conveying fan with a control method suited to each parking lot, rather than controlling the conveying fan with a uniform control method for multiple parking lots. For this purpose, learning device 200 is used.

[0069] FIG. 13 is a schematic diagram showing a ventilation system 130 related to learning by the learning device 200. The ventilation system 130 further includes an environmental sensor 40 in addition to the ventilation system 100 of embodiment 1. The environmental sensor 40 is installed on a pillar or the like in the parking lot and measures the concentration of pollutants in the air. In order to grasp the air quality in the entire parking lot, multiple environmental sensors 40 are installed in different locations in the parking lot, including the center and peripheral areas. The pollutant concentrations measured by the environmental sensor 40 are used for learning by the learning device 200.

[0070] Gases that should be ventilated as exhaust from parking lots include CO and NOx. Therefore, each environmental sensor 40 measures the CO concentration and NOx concentration as the concentration of pollutants. CO is slightly lighter than air and moves upward toward the ceiling over time. NOx is heavier than air and moves downward toward the floor over time. Because the concentration around the mouth and nose of a person standing is the most problematic, it is desirable to install each environmental sensor 40 1 to 2 meters above the floor of the parking lot.

[0071] The NOx sensors and CO sensors used as each environmental sensor 40 are expensive, and it is not practical to install them permanently in a parking lot. In this embodiment, multiple environmental sensors 40 are loaned for a fixed period of time, and the learning device 220 performs learning during the loan period. When the learning period ends, the multiple environmental sensors 40 are collected and loaned to ventilation systems installed in other parking lots to be used for learning. Using the environmental sensors 40 in multiple parking lots in turn to perform learning in this way is advantageous in terms of initial cost.

[0072] The learning device 200 and the inference device 300 will be described below in terms of a learning phase and an application phase.

[0073] 14 is a block diagram showing the configuration of the learning device 200. The learning device 200 includes a data acquisition unit 21 and a model generation unit 22. The data acquisition unit 21 acquires learning data from the ventilation system 130. The learning data includes air volume data indicating the air volume of each of the conveying fans 90-1 to 90-4 and image data of an image captured inside the parking lot.

[0074] The image data is data of images captured by the cameras 20-1 and 20-2, respectively. The air volume data is data indicating the air volume of each conveyance blower, and is specifically expressed as data indicating the operating parameters or operating mode of each conveyance blower that determine the air volume. The air volume data for a conveyance blower whose air volume has been changed by the control unit 30 based on the image data is changed to data indicating the changed air volume. The learning data acquired by the data acquisition unit 21 is output to the inference unit 42.

[0075] The model generation unit 22 learns an air volume control command for controlling the air volume of the conveyance blower based on the learning data. That is, the model generation unit 22 generates a learned model that infers optimal air volume control information from the learning data acquired from the ventilation system 110.

[0076] Learning device 200 is connected to ventilation system 130. Learning device 200 is preferably connected to, for example, network 140 (see FIG. 2 ) and acquires learning data via network 140. In this case, learning device 200 may exist on a cloud server. Alternatively, learning device 200 may be built into ventilation system 130.

[0077] The learning algorithm used by the model generation unit 22 can be a known algorithm such as supervised learning, unsupervised learning, or reinforcement learning. As an example, a case where reinforcement learning is applied will be described. In reinforcement learning, an agent (acting subject) in a certain environment observes the current state (environmental parameters) and decides on an action to be taken. The environment changes dynamically depending on the agent's actions, and the agent is given a reward according to the change in the environment. The agent repeats this process and learns the course of action that will obtain the most reward through a series of actions. Q-learning and TD-learning are known as representative reinforcement learning methods. For example, in the case of Q-learning, a general update formula for the action value function Q(s, a) is expressed by Equation 1.

[0078]

[0079] In Equation 1, st represents the state of the environment at time t, and at represents the action at time t. The state changes to st+1 due to the action at. rt+1 represents the reward obtained due to the change in state, γ represents the discount rate, and α represents the learning coefficient. γ is in the range of 0<γ≦1, and α is in the range of 0<α≦1. The air volume of the conveying fans 90-1 to 90-4 represents the action at, the image captured inside the parking lot represents the state st, and the best action at for the state st at time t is learned.

[0080] The update formula expressed by Equation 1 increases the action value Q if the action value Q of the action a with the highest Q value at time t+1 is greater than the action value Q of the action a executed at time t, and decreases the action value Q in the opposite case. In other words, the action value function Q(s, a) is updated so that the action value Q of the action a at time t approaches the best action value at time t+1. As a result, the best action value in a certain environment is propagated sequentially to the action value in the previous environment.

[0081] When generating a trained model using reinforcement learning in this manner, the model generation unit 22 includes a reward calculation unit 22a and a function update unit 22b. The reward calculation unit 22a calculates a reward based on the training data. The reward calculation unit 22a calculates a reward r based on a reward criterion. The reward criterion here is the CO concentration and NOx concentration measured by the multiple environmental sensors 40, and the respective concentration data is acquired by the data acquisition unit 21. For example, if the measured CO concentration and NOx concentration decrease as a result of operating the conveying blowers 90-1 to 90-4 at the air volume indicated by the air volume data, the reward calculation unit 22a increases the reward r (for example, provides a reward of "1"). On the other hand, if the measured CO concentration and NOx concentration increase as a result of operating the conveying blowers 90-1 to 90-4 at the air volume indicated by the air volume data, the reward calculation unit 22a reduces the reward r (for example, provides a reward of "-1").

[0082] The function update unit 22b updates the function for determining air volume control information for controlling the conveyance fans 90-1 to 90-4 in accordance with the reward calculated by the reward calculation unit 22a, and outputs the updated function to the trained model storage unit 23. For example, in the case of Q-learning, the action value function Q(st, at) expressed by Equation 1 is used as a function for calculating the air volume control information.

[0083] The learning process described above is repeated. The learned model storage unit 23 stores the action value function Q(st, at) updated by the function update unit 122b, i.e., the learned model. The learned model storage unit 23 is provided outside the learning device 200, but may also be a storage unit built into the learning device 200.

[0084] Next, the learning process performed by the learning device 200 will be described with reference to Fig. 15. Fig. 15 is a flowchart showing the operation of the learning device 200.

[0085] In step b1, the data acquisition unit 21 acquires air volume data of the conveying fans 90-1 to 90-4 and image data of the parking lot as learning data. In step b2, the model generation unit 22 calculates a reward based on the learning data. Specifically, the reward calculation unit 22a acquires the learning data and determines whether to increase or decrease the reward based on the CO concentration and NOx concentration measured by the multiple environmental sensors 40.

[0086] If the exhaust gas in the parking lot decreases as a result of the conveying fans 90-1 to 90-4 operating at the air volume indicated by the air volume data, the remuneration calculation unit 22a determines in step b3 to increase the remuneration and increases the remuneration. On the other hand, if the exhaust gas in the parking lot increases as a result of the conveying fans 90-1 to 90-4 operating at the air volume indicated by the air volume data, the remuneration calculation unit 22a determines in step b4 to decrease the remuneration and decreases the remuneration.

[0087] In step b5, based on the reward calculated by the reward calculation unit 22a, the function update unit 22b updates the action value function Q(st, at) expressed by Equation 1 stored in the learned model storage unit 23. The learning device 200 repeatedly executes the above steps b1 to b5, and stores the generated action value function Q(st, at) as a learned model in the learned model storage unit 23.

[0088] The hardware configuration of the learning device 200 is the same as that shown in FIG. 4, and includes a processor, memory, and bus 72, or includes a dedicated processing circuit.

[0089] In this way, the learning device 200 performs learning based on learning data including the air volume data of the conveyance fans 90-1 to 90-4 and image data of the parking lot. Through this learning, a trained model can be obtained that infers air volume control information suited to the parking lot where the ventilation system 130 is installed.

[0090] <Utilization phase>

[0091] 16 is a block diagram showing the configuration of the inference device 300. The inference device 300 includes a data acquisition unit 41 and an inference unit .

[0092] The data acquisition unit 41 acquires input data from the ventilation system 130 after the learning period. The input data includes image data of images captured inside the parking lot. The image data is data of images captured by the cameras 20-1 and 20-2. The input data acquired by the data acquisition unit 41 is output to the inference unit 42.

[0093] The inference unit 42 reads out the trained model stored in the trained model storage unit 23 and uses this trained model to infer air volume control information. That is, by inputting the input data acquired by the data acquisition unit 41 into this trained model, it is possible to output air volume control information suitable for the image data.

[0094] The inference device 300 is connected to the ventilation system 130. The inference device 300 is connected to, for example, a network 140 (see FIG. 2 ) and acquires input data via the network 140. In this case, the inference device 300 may exist on a cloud server. Alternatively, the inference device 300 may be built into the ventilation system 130. Note that when the inference device 300 is used after the learning period, the multiple environmental sensors 40 are removed from the ventilation system 130, as described above.

[0095] Although the inference device 300 has been described as inferring air volume control information using a trained model trained based on the ventilation system 130, it may also be configured to obtain a trained model trained using another ventilation system and output air volume control information based on this trained model.

[0096] Next, the process for obtaining air volume control information using the inference device 300 and the operation of the ventilation system 130 will be described with reference to Fig. 17. Fig. 17 is a flowchart showing the operation of the inference device 300 and the ventilation system 100.

[0097] In step c1, the data acquisition unit 41 acquires input data. In step c2, the inference unit 42 reads out the trained model stored in the trained model storage unit 23 and obtains air volume control information by inputting the input data acquired by the data acquisition unit 151 into this trained model. The air volume control information includes information identifying at least one of the conveyance blowers 90-1 to 90-4 whose air volume should be changed, and information identifying the air volume after the change for each of the identified conveyance blowers.

[0098] In step c3, the inference unit 42 outputs the obtained air volume control information to the control unit 30 of the ventilation system 130. In step c4, the control unit 30 of the ventilation system 130 controls the air volume of at least one of the identified conveyance blowers 90-1 to 90-4 based on the air volume control information obtained from the inference unit 42. Specifically, the blower control unit 33 generates an air volume control command based on the air volume control information obtained from the inference unit 42, and transmits the command to the conveyance blower whose air volume should be increased.

[0099] The hardware configuration of the inference device 300 is similar to that shown in FIG. 4, and includes a processor, memory, and bus 72, or includes a dedicated processing circuit.

[0100] In this way, the inference device 300 infers air volume control information for controlling the air volume of the conveyance blower based on the trained model trained by the learning device 200, and can provide the ventilation system with control of the conveyance blower that is suited to the parking lot in which the ventilation system 130 is installed. The ventilation system 130, in which the conveyance blower is controlled by this inferred air volume control information, can provide efficient ventilation in accordance with the movement of vehicles, improving the air quality in the parking lot.

[0101] In the learning device 200 according to this embodiment, air volume data indicating the respective air volumes of the intake air blower 5 and the exhaust air blower 6 may also be added to the learning data. In this case, the inference device 300 further acquires, as input data, air volume data indicating the respective air volumes of the intake air blower 5 and the exhaust air blower 6. Therefore, in the ventilation system 130 operating after the learning period, the intake air blower 5 and the exhaust air blower 6 are also adjusted to appropriate air volumes to provide efficient ventilation.

[0102] Furthermore, in the learning device 200, the learning data for the learning device 200 may include vehicle position data indicating the position of the vehicle instead of or in addition to image data. The vehicle position data is vehicle position information detected from the image data by the control unit 30 (specifically, the vehicle movement detection unit 31). The vehicle position data is used in reinforcement learning as a parameter indicating behavior.

[0103] In this embodiment, a case where supervised learning is applied to the learning algorithm used by the model generation unit 22 has been described, but the present invention is not limited to this. As for the learning algorithm, reinforcement learning, unsupervised learning, semi-supervised learning, or the like can also be applied in addition to supervised learning.

[0104] Furthermore, the learning algorithm used in the model generation unit 22 may be deep learning, which learns to extract the features themselves, or machine learning may be performed according to other known methods, such as neural networks, genetic programming, functional logic programming, and support vector machines.

[0105] The model generation unit 22 may also learn air volume control information according to learning data created for multiple ventilation systems. The model generation unit 22 may acquire learning data from multiple ventilation systems used in the same parking lot, or may learn air volume control information using learning data collected from multiple ventilation systems operating independently in different parking lots. It is also possible to add a ventilation system from which learning data is collected to the target system during the process, and it is also possible to remove that ventilation system from the target system. Furthermore, a learning device that has learned air volume control information for a certain ventilation system may be applied to another ventilation system, and the air volume control information for the other ventilation system may be re-learned and updated.

[0106] The ventilation system for the study may be, instead of the ventilation system 130, the ventilation system 110 of embodiment 2 in which multiple environmental sensors 40 are installed, or the ventilation system 110 of embodiment 3 in which multiple environmental sensors 40 are installed.

[0107] The embodiments disclosed herein are illustrative, and modifications, omissions, or additions of components are possible in each embodiment without departing from the scope of the claims.

[0108] 1 Air intake port, 2 Exhaust port, 5 Air intake fan, 6 Exhaust fan, 10, 10-1, 10-2 Vehicle movement path, 11 Vehicle, 12-1 to 12-4 Air flow, 20 Imaging unit, 20-1, 20-2 Camera, 21, 41 Data acquisition unit, 22 Model generation unit, 30 Control unit, 31 Vehicle movement detection unit, 32 Vehicle shape detection unit, 33 Fan control unit, 40 Environmental sensor, 42 Inference unit, 90, 90-1 to 90-4 Transport fan, 91A to 91D Air path, 100, 110, 120, 130, 140 Ventilation system, 200 Learning device, 300 Inference device

Claims

1. an intake air blower that supplies outside air to the parking lot through an intake port; an exhaust fan that exhausts air from the parking lot to the outside through an exhaust port; a conveying fan that conveys an airflow from the intake fan to the exhaust fan; an imaging unit that captures an image of the interior of the parking lot and outputs image data; a control unit that detects a moving vehicle in the parking lot based on image data output from the imaging unit, further detects the size of the detected moving vehicle, and changes the air volume of the conveyance blower in accordance with the size of the moving vehicle; A ventilation system comprising:

2. There are a plurality of conveying blowers, the imaging unit includes a plurality of cameras, The ventilation system described in claim 1, characterized in that the control unit compares the sizes of the vehicles imaged by the multiple cameras, identifies at least one of the multiple conveying blowers based on the comparison results, determines the air volume of the identified conveying blower, and changes it for a predetermined period of time.

3. A data acquisition unit that acquires learning data including at least one of image data showing an image of a parking lot in which a conveying fan is installed and vehicle position data showing the position of a vehicle in the parking lot, and air volume data showing the air volume of the conveying fan in the one of the data; and a model generation unit that generates a trained model for inferring air volume control information for controlling the air volume of the conveying fan from at least one of an image of the parking lot and a position of a vehicle in the parking lot, using the training data; A learning device comprising:

4. The data acquisition unit acquires concentration data indicating the concentration of CO and the concentration of NOx in the parking lot, 4. The learning device according to claim 3, wherein the model generation unit generates a trained model for inferring the air volume control command using the concentration data as a reward criterion.

5. A data acquisition unit that acquires at least one of image data showing an image of a parking lot in which a conveying fan is installed and vehicle position data showing the position of a vehicle in the parking lot; and An inference device characterized by comprising an inference unit that uses a trained model for inferring the air volume of the conveying fan from at least one of an image of the parking lot and the position of the vehicle in the parking lot, and outputs air volume control information for controlling the air volume of the conveying fan from at least one of the data acquired by the data acquisition unit.