JP7370821B2 - Perimeter air conditioning system - Google Patents

Description

Application of Article 30, Paragraph 2 of the Patent Act Proceedings of the 2019 Society of Air Conditioning and Sanitary Engineers Conference, pp. 337-340

The present invention relates to an air conditioning system that performs air conditioning in a perimeter zone.

FIG. 11 schematically shows an example of a general air conditioning system. Conditioned air (supply air) A1 sent out from the air conditioner 1 is guided to a target space S, which is an indoor room such as an office, through an air supply duct 2. A plurality of air outlets 4 are installed in the ceiling 3 of the target space S, and the downstream side of the air supply duct 2 extending from each air conditioner 1 is connected to each air outlet 4. Conditioned air A1 flowing through the air supply duct 2 is supplied to the target space S from each outlet 4.

A variable air volume device 5 is provided at a position in front of each outlet 4 in the air supply duct 2. The variable air volume device 5 is a device abbreviated as VAV (Variable Air Volume), and is adapted to adjust the volume of air passing through the inside by changing the opening degree of a damper provided inside. When the supply air A1 is supplied to the target space S, the air volume is adjusted by the variable air volume device 5.

The target space S can be divided into a perimeter zone P such as a window area that is easily affected by the outer skin load, and an interior zone I inside the perimeter zone P. FIG. 11 shows one variable air volume device 5 at a position facing the interior zone I and one at a position facing the perimeter zone P, and the variable air volume device 5 facing the interior zone I is supplied with air. One air conditioner 1 (interior air conditioner 1a) that sends out air A1 and one air conditioner 1 (perimeter air conditioner 1b) that sends out supply air A1 to variable air volume device 5 facing perimeter zone P are shown. (This is a schematically simplified diagram, and in an actual air conditioning system, the number and arrangement of variable air volume devices 5 and air conditioners 1, the number of variable air volume devices 5 for air conditioners 1, etc. are subject to change.) It goes without saying that it is set as appropriate depending on the scale and shape of the space S, the thermal situation, etc.).

Suction ports 7 and 16 are provided in the ceiling 3 at positions corresponding to the interior zone I and the perimeter zone P, respectively. From each variable air volume device 5 facing the interior zone I and the perimeter zone P, supply air A1 sent from the interior air conditioner 1a or the perimeter air conditioner 1b is supplied to the target space S through the outlet 4, and It mixes with the air (indoor air) A2 in the space S.

A portion of the indoor air A2, mainly located in the interior zone I, is taken in as return air A3 from the suction port 7 facing the interior zone I. Part of the return air A3 is discharged outside the return air duct 8 as exhaust air A4, and part of it mixes with outside air A0 newly taken in from the return air duct 8 and returns to the interior air conditioner 1a, where the temperature and humidity are After the air is adjusted, it is sent out again as supply air A1.

A portion of the indoor air A2, mainly located in the perimeter zone P, is taken in as return air A3 from the suction port 16 facing the perimeter zone P, and the entire amount returns to the perimeter air conditioner 1b through the return air duct 17. After the temperature is adjusted, it is sent out again as supply air A1. In this way, air is circulated between the air conditioner 1 and the target space S.

In such an air conditioning system, for example, an air conditioning method called a variable air volume method is used to cope with fluctuations in the air conditioning load within the target space S. A temperature sensor 9 is provided at a suitable location within the target space S (in the example shown here, the ceiling 3) to measure the temperature of the indoor air A2. Each variable air volume device 5 is provided with a control device (VAV controller), which controls the variable air volume device 5 so that the deviation between the measured value by the temperature sensor 9 and the temperature set value in the variable air volume device 5 is zero. Control is performed using PI control or the like, and an appropriate amount of air A1 is supplied from the outlet 4. For example, during heating, if the measured value of the temperature sensor 9 is lower than the set value of the indoor temperature (temperature of the indoor air A2), the supply amount of the air supply A1 is increased, and if the set value and the measured value are close control such as reducing the supply amount.

The operating status of each device constituting the air conditioning system is monitored and operated by the control device 10. The control device 10 includes a controller that controls the operation of each air conditioner 1 (interior air conditioner 1a and perimeter air conditioner 1b), an intelligent gateway that connects to a central monitoring network, and the like. Values such as the air volume and the set temperature in the target space S are acquired, and based on these values, the temperature, air volume, etc. of the supply air A1 supplied from each air conditioner 1 are determined.

The control device of each variable air volume device 5 acquires the measured value of each temperature sensor 9, adjusts the opening degree of the damper in the variable air volume device 5 based on the deviation from the set temperature, and supplies air A1 with an appropriate air volume. is supplied from the air outlet 4. That is, for example, during heating, if the measured value of the temperature sensor 9 is significantly lower than the set value of the indoor temperature (temperature of the indoor air A2), the supply amount of the air supply A1 is increased so that the set value and the measured value are If the amount is close, control is performed to reduce the supply amount.

In each air conditioner 1, the supply air A1 sent from the variable air volume device 5 is sent to each variable air volume device 5, and the amount of the supply air A1 sent here is the sum of the required air volume in the variable air volume device 5 downstream. be. Therefore, the control device 10 determines the amount of air supplied to each air conditioner 1 based on the required air amount in each variable air amount device 5.

In addition to the control based on air volume as described above, in an actual air conditioning system, there is also control (load reset control) that adjusts the supply air temperature (temperature of supply air A1 sent from air conditioner 1) according to the required air volume. It will be done. In a variable air volume type air conditioning system, it can be said that, in principle, if the load is large, the required air volume from the variable air volume device 5 increases, and if the load is small, the required air volume decreases. Therefore, in response to the required air volume from the variable air volume device 5, not only the air volume of the air supply A1 supplied to the air conditioner 1 but also the temperature of the air supply is changed as appropriate. For example, during heating, if the required air volume is smaller than the rated air volume of the variable air volume device 5, the set value of the supply air temperature is lowered. Note that various methods can be adopted for the load reset control. For example, based on the opening degree information of the variable air volume devices 5, the supply air temperature is adjusted so that the opening degree of each variable air volume device 5 falls within a predetermined opening range. A method may be used in which the set value is changed, or the deviation between the set temperature of the variable air volume device 5 and the measured temperature (measured temperature of air at an appropriate location in the air conditioning system, for example, the temperature of return air A3) is weighted. A method may also be used in which the set value of the supply air temperature is changed based on the weighting.

In this way, in the air conditioning system as shown in FIG. 11, the supply air volume and supply air temperature are automatically changed according to the indoor load.

By the way, in such an air conditioning system, since the temperature of the indoor air A2 is grasped as the measured value of the temperature sensor 9, the temperature of the indoor air A2 that a person in the target space S is actually in contact with and the control device 10 are The detected temperature of the indoor air A2 may deviate. In the example shown in FIG. 11, the temperature sensor 9 is arranged at the height of the ceiling 3, but depending on the outside air conditions and the control conditions of each device such as the variable air volume device 5 and the air conditioner 1, etc., the temperature sensor 9 may be placed near the floor surface where the person is located. This results in a difference between the temperature of the indoor air A2 in the vicinity of the temperature sensor 9 and the temperature of the indoor air A2 in the vicinity of the temperature sensor 9.

In particular, in winter when the outside air temperature is low, the indoor air A2 in the perimeter zone P is cooled by the outside air, creating a flow of cold air called a cold draft that sinks downward and flows along the floor surface. A situation may arise in which people located in or near the perimeter zone P feel uncomfortable. Warm air has a lower specific gravity than cold air, so even if warm air is supplied from the air outlet 4 in the ceiling 3, if the temperature difference between the warm air and cold air is large or the air volume is insufficient, the air will flow from the air outlet 4. It is assumed that the inertial force of the downward blown air is canceled out by the upward buoyant force, and the air does not reach near the floor surface.

Therefore, in the example shown here, a perimeter fan 6 is provided near the floor surface of the perimeter zone P for the purpose of correcting the temperature distribution of the indoor air A2 in the perimeter zone P. The perimeter fan 6 is configured to send indoor air A2 in the target space S upward along the window surface. By operating this perimeter fan 6, if a flow of indoor air A2 is formed upward from near the floor surface of the perimeter zone P, the indoor air A2 near the window surface cooled by the outside air becomes a cold draft and flows into the perimeter zone P. It is possible to prevent the air from moving toward the inner interior zone I and to send it to the upper suction port 16. In addition, if the indoor air A2 is sent out from the nearby variable air volume device 5 toward the perimeter fan 6, in conjunction with the operation of the perimeter fan 6, the high temperature indoor air A2 is sent to the perimeter zone P. It is also possible to supply the liquid to the vicinity of the outer edge.

Prior art documents related to this type of air conditioning system include, for example, the following Patent Document 1 (However, in the case of the air conditioning system described in Patent Document 1, the portion corresponding to the perimeter fan 6 in FIG. (This is different from the example shown in Fig. 11 in that it is equipped with a fan coil unit and can heat indoor air even in this position.)

In addition, for convenience of explanation, in FIG. 11, two air conditioners 1, one target space S, two air outlets 4, two variable air volume devices 5, and one perimeter fan 6, a total of two Although the suction ports 7 and 16 are simply illustrated, in an actual air conditioning system, the number of installed air conditioners 1 and variable air volume devices 5 may be changed, or the air supply A1 may be introduced into multiple target spaces S. good. The number of air outlets 4 installed per target space S can also be changed as appropriate depending on the size of the target space S and the like. In addition, in an actual air conditioning system, various devices and sensors are installed in addition to the devices shown here, but illustrations of configurations that are not directly related to the purpose of the present invention are omitted as appropriate. .

Japanese Patent Application Publication No. 2018-136074

As mentioned above, the perimeter fan 6 is provided to correct the temperature distribution in the perimeter zone P. However, if the temperature of the indoor air A2 near the perimeter fan 6 is not correctly grasped, even this may be insufficient.

That is, as shown in FIG. 11, when the temperature sensor 9 is provided at a position on the ceiling 3, the operation of the nearby variable air volume device 5 is determined based on the measured temperature at this position. Therefore, if a sufficient amount of warm air cannot be supplied from the variable air volume device 5 to the perimeter fan 6, or if there is a temperature difference in the air between the upper and lower parts of the room, the floor surface near the perimeter zone P The actual temperature situation in the vicinity is not reflected in the operation of the variable air volume device 5, and even if the ceiling 3 is maintained at a comfortable temperature, a situation may occur in which the temperature in the living area becomes low. .

Incidentally, if a fan coil unit is provided at the position of the perimeter fan 6 in FIG. 11 to heat the indoor air A2, as in the technology described in Patent Document 1, it is possible to suppress the occurrence of the above-mentioned temperature situation. However, coils for heat exchange, piping for circulating heat medium, etc. are required separately, which increases construction costs and running costs.

In view of these circumstances, the present invention seeks to provide an air conditioning system that can suitably correct the air temperature distribution in the perimeter zone.

The present invention includes an air conditioner that sends out air supply;
an air supply duct that guides air supply from the air conditioner to the target space;
An air outlet that blows out air into the target space;
a variable air volume device that adjusts the air volume of the supply air blown out from the air outlet;
A perimeter fan that is installed in the perimeter zone and sends indoor air upward;
and a suction port provided above the perimeter fan,
Measuring at least part of the temperature near the floor from indoor air near the floor taken into the perimeter fan,
A temperature estimation model generated by machine learning is used to calculate the temperature near the floor at each position in the perimeter zone based on the parameter that is the temperature near the floor of at least some of the parameters and the parameter related to the temperature near the floor in the perimeter zone. The present invention relates to an air conditioning system characterized in that the air conditioning system is configured to adjust the amount of air blown from the variable air amount device facing the perimeter zone based on the estimated near-floor temperature.

In the air conditioning system of the present invention, the temperature estimation model is a model that is generated based on learning data and estimates the temperature near the floor using various parameters as explanatory variables;
The learning data may be a data set in which a plurality of parameters related to the temperature near the floor and an actual measured value of the temperature near the floor when the air conditioning system is actually operated are recorded.

In the air conditioning system of the present invention, the temperature estimation model can be generated using a neural network.

The air conditioning system of the present invention includes a near-floor temperature sensor that measures near-floor temperature from indoor air near the floor,
The temperature estimation model can be configured to estimate the temperature near the bed using some or all of the parameters selected from the following parameters as explanatory variables.
・Outside temperature, wind direction, wind speed, rainfall amount, solar radiation amount, measured value of the temperature sensor near the floor, operating status of the air conditioner, operating status of the perimeter fan, operating status of the variable air volume device facing the perimeter zone, Measured values, date, time, and day of the week of the temperature sensor installed in the target space

In the air conditioning system of the present invention, at least the outside air temperature, the amount of solar radiation, the measured value of the temperature sensor near the floor, the measured value of the temperature sensor, and the operating state of the perimeter fan can be used as explanatory variables.

In the air conditioning system of the present invention, the adjustment of the blowout air volume of the variable air volume device based on the estimated floor temperature may be performed by adding a temperature correction value to the set temperature of the variable air volume device. .

In the air conditioning system of the present invention, the temperature correction value can be configured to be adjustable based on a deviation between the estimated near-floor temperature and the set temperature in the variable air volume device.

In the air conditioning system of the present invention, the temperature correction value can be configured to be determined using PI control.

The air conditioning system of the present invention can be configured to add a temperature correction value to the set temperature in the variable air volume device facing the perimeter zone when the outside air temperature is lower than a threshold value.

The air conditioning system of the present invention can be configured to lower the upper limit value of the supply air temperature in the air conditioner when the outside air temperature is lower than a threshold value.

According to the air conditioning system of the present invention, it is possible to achieve the excellent effect of suitably correcting the air temperature distribution in the perimeter zone.

1 is a schematic diagram showing an example of the configuration of an air conditioning system to which the present invention is applied. FIG. 2 is a schematic plan view showing an example of the arrangement of a variable air volume device and a near-floor temperature sensor installed facing a perimeter zone in an air conditioning system to which the present invention is applied. 1 is a schematic diagram showing an example of the overall configuration of an air conditioning system of the present invention applied to a building with multiple floors. FIG. 2 is a schematic plan view showing an example of the arrangement of a variable air volume device and a near-floor temperature sensor installed facing a perimeter zone of a reference floor in an air conditioning system to which the present invention is applied. 2 is a flowchart illustrating an example of a procedure for setting operating conditions of a variable air volume device, etc. in an embodiment of the present invention. FIG. 2 is a conceptual diagram illustrating a temperature difference between upper and lower indoor air and temperature control based on the difference. It is a graph explaining an example of the relationship between the control deviation calculated based on the estimated value of the floor vicinity temperature, and the temperature correction value. It is a graph explaining an example of the relationship between outside air temperature and the upper limit value of supply air temperature. FIG. 2 is a schematic diagram illustrating an example of the temperature distribution of indoor air near a perimeter zone of the air conditioning system in FIG. 1. FIG. It is a block diagram conceptually explaining control using a temperature correction value in a present example. 1 is a schematic diagram showing an example of the configuration of a conventional air conditioning system.

Embodiments of the present invention will be described below with reference to the accompanying drawings.

As shown in FIG. 1, air supply A1 sent out from an air conditioner 1 is guided to a target space S, which is an indoor room such as an office, through an air supply duct 2, and is blown out from a plurality of air outlets 4 installed in a ceiling 3. be done. A variable air volume device 5 is provided at a position in front of each outlet 4, and the supply air A1 is supplied to the target space S after the air volume is adjusted by the variable air volume device 5. A portion of the indoor air A2 is taken in as return air A3 from suction ports 7 and 16 provided in the ceiling 3 above, and is returned to the air conditioner 1 through return air ducts 8 and 17. At this time, part of the return air A3 taken into the return air duct 8 from the suction port 7 of the interior zone I is exhausted as exhaust air A4, and is returned to the interior air conditioner 1a together with the newly taken in outside air A0. ing. On the other hand, the entire amount of return air A3 taken into the return air duct 17 from the suction port 16 of the perimeter zone P is returned to the perimeter air conditioner 1b. A temperature sensor 9 for measuring the temperature of the indoor air A2 is provided at a suitable position in the target space S at the height of the ceiling 3, and the temperature of the indoor air A2 at this position is measured. A perimeter fan 6 is installed in the perimeter zone P, and is configured to send indoor air A2 near the floor surface upward along the window surface.

As described above, the air conditioning system of this embodiment has the same basic configuration as the conventional example shown in FIG. 11, but in the case of this embodiment, as shown in FIGS. Of the variable air volume devices 5 located near the variable air volume devices 5, near-floor temperature sensors 11 are provided near some of the variable air volume devices 5 in a plan view (FIG. 1 shows the temperature sensors 11 near the floor in a side view). (The location is indicated by a dashed line). The near-floor temperature sensor 11 is a sensor installed at or near the floor surface at a height where people or the like exist in the perimeter zone P, and measures the temperature of the surrounding air. The air temperature near the floor at various locations in the perimeter zone P (hereinafter referred to as "near-floor temperature" for simplicity) acquired by the near-floor temperature sensor 11 is used to estimate the near-floor temperature at another location. . The estimated near-floor temperature is used to set the amount of air blown from the variable air volume device 5 facing that position.

The term "temperature near the floor" as used herein refers to the temperature of the air in the vicinity of the floor, which is 0 cm or more and less than 10 cm, or in the living area, which is 10 cm or more and less than 170 cm. In addition, the near-floor temperature sensor 11 that measures the temperature near the floor may be installed at a height of 0 cm or more and less than 10 cm when measuring the temperature of the floor surface or its vicinity, and when measuring the temperature of the living area. It may be provided at a height of 10 cm or more and 170 cm or less.

The installation position of the near-floor temperature sensor 11 in plan view is preferably inside each perimeter fan 6 (see FIG. 1). The perimeter fan 6 is usually arranged so as to take in the indoor air A2 from the side facing the inside of the target space S and send it upward. Therefore, when the near-floor temperature sensor 11 is provided inside the perimeter fan 6, the indoor air A2 near the floor taken into the perimeter fan 6 comes into contact with the near-floor temperature sensor 11 while moving. The sensor 11 can suitably obtain the temperature near the bed.

Such an air conditioning system can be installed in the entire building, as shown in FIG. 3, for example, and on each floor, as shown in FIG. Regarding this, a near-floor temperature sensor 11 is installed at a position near it in plan view. In the example shown here, with respect to the perimeter zone P of each target space S, one near-floor temperature sensor 11 is installed on each side in plan view (note that the "perimeter zone P" ``variable air volume device 5'' means ``variable air volume device 5 that supplies air to the perimeter zone P''). The temperature situation in the perimeter zone P is easily affected by the external load (wind direction, sunlight, etc.) through the window surfaces and walls facing the outside air, and even within the same building or target space S, the orientation of the window surfaces and walls This is because although the temperature varies greatly depending on the situation, if the room is in the same room and the direction relative to the building is the same, it is thought that the temperature will be roughly the same. That is, for example, when estimating the near-floor temperature at various points in the perimeter zone P facing the north wall in a certain target space S, the measured value of the near-floor temperature sensor 11 provided only on the north side is used as one of the explanatory variables. It can be used as one.

In other words, the perimeter zone P of each target space S on each floor can be roughly divided into four systems depending on the characteristics of the temperature situation, which differ depending on the direction. The target space S with windows and walls can be considered to have two perimeter zones: a northeast perimeter zone P and a northwest perimeter zone P (note that floors with special shapes or Regarding the target space S, this is not limited to this, of course, and it can be assumed that the target space S can be considered to have more peripheral zones P). Then, a temperature estimation model M, which will be described later, is generated for each perimeter zone P corresponding to each of these systems. At this time, at least one near-floor temperature sensor 11 is provided for each system of the perimeter zone P (side corresponding to each direction in a plan view of the building), and the measured values of these near-floor temperature sensors 11 are used as one of the explanatory variables. When used as one, it becomes possible to estimate the temperature near the floor taking into account the influence of direction.

The division of perimeter zones according to direction as explained above and the creation of a temperature estimation model based on this are just examples, and in order to actually generate a temperature estimation model, it is necessary to divide the perimeter zones and create a temperature estimation model. The method of creating the model can be set as appropriate depending on the temperature situation at the site. For example, if the temperature situation is considered to be different even in the same room and in the same direction, two or more near-floor temperature sensors 11 can be installed and the measured values of each can be used as explanatory variables. (At this time, you may create a temperature estimation model that uses the measured values of each near-floor temperature sensor 11, or you may create a temperature estimation model that uses the measured values of multiple near-floor temperature sensors 11 as explanatory variables. (a temperature estimation model may also be generated).

Alternatively, for example, the near-floor temperature sensors 11 are provided in the northeast perimeter zone and the northwest perimeter zone, respectively, and one temperature estimation model is generated that uses the measured values of the plurality of near-floor temperature sensors 11 as explanatory variables. It is also possible to estimate the near-floor temperature at other positions in the northeast and northwest perimeter zones. When increasing the number of temperature estimation models generated, the accuracy of estimating the temperature near the floor improves, but the amount of calculation increases, so this method is effective when it is necessary to save the amount of calculation. .

Although FIG. 2 only shows the variable air volume device 5 installed in the perimeter zone P and the near-floor temperature sensor 11, in reality, the variable air volume device 5 is also appropriately arranged in the interior zone I. It goes without saying that other equipment such as the perimeter fan 6 and the temperature sensor 9 are also arranged as shown in FIG. In addition, FIG. 3 shows a simplified building and air conditioning system as an overall diagram of the air conditioning system, and also shows one air conditioner 1 (perimeter air conditioner 1b) and variable air volume device 5 on each floor. It goes without saying that the actual number of floors of the building may be different from the number of floors shown here, and that more air conditioners 1 and variable air volume devices 5 may be installed on each floor. Of course, the floor plan of each floor and the arrangement of the variable air volume device 5 in each target space S may be different from the configuration shown in FIG. 2.

On some floors of the building, near-floor temperature sensors 11 are installed near all of the variable air volume devices 5 facing the perimeter zone P, as shown in FIG. . This is to collect actual measured values of the temperature near the floor, which will be used as learning data D (see FIG. 3) for generating a temperature estimation model M to be described later.

As shown in FIG. 4, the floor where the near-floor temperature sensors 11 are installed for all units of the variable air volume device 5 facing the perimeter zone P (hereinafter referred to as the "standard floor") is, for example, a floor where multiple units with a common floor plan are installed. It is preferable to select a specific part of the floors. This is because if the floor plans are the same, the temperature conditions are likely to be roughly the same. In other words, for example, in a building with the same floor plan from the 11th to 40th floors, if the 11th to 40th floors are the target, the 25th floor is set as the reference floor, and the actual measured temperature near the floor collected on the 25th floor may be used as the learning data D to generate the temperature estimation model M, and use it to estimate the temperature near the floor on other floors from the 11th floor to the 40th floor. In addition, even if the floor plans are the same, if the heights are significantly different, there may be differences in temperature conditions, so in such cases, for example, the 18th floor and the 32nd floor may be set as separate standard floors. good. That is, a first temperature estimation model is generated based on the learning data collected using the 18th floor as the first reference floor, and is used to estimate the temperature near the floor on other floors from the 11th floor to the 24th floor. A second temperature estimation model is generated based on the learning data collected as the second reference floor, and is used to estimate the temperature near the floor on other floors from the 25th floor to the 40th floor. Alternatively, for example, in a case where the temperature situation changes significantly at a specific floor due to the influence of the shadow of a nearby building, different temperature estimation models may be applied above and below the specific floor. In this way, the setting of the reference floor and the target to which a certain temperature estimation model is applied may be appropriately determined in consideration of various conditions.

The air conditioning on each floor is operated by an air conditioner 1, a variable air volume device 5, a perimeter fan 6, a temperature sensor 9, a near-floor temperature sensor 11, and a control device 10 as shown in FIG. It is monitored and controlled by a central monitoring device 12 connected to the control device 10. The central monitoring device 12 is a device that comprehensively monitors the air conditioning system of the entire building. A temperature estimation section 13 is further connected to the central monitoring device 12, and a model generation section 14 is connected to the temperature estimation section 13. The temperature estimation unit 13 and the model generation unit 14 are, for example, information processing devices such as personal computers. The temperature estimation unit 13 estimates the temperature near the floor in the perimeter zone P (see FIGS. 1 and 2) of each floor, as described later. The model generation unit 14 generates a temperature estimation model M for the temperature estimation unit 13 to estimate the temperature near the floor. The temperature estimation model M is generated based on the learning data D, and uses various parameters as explanatory variables in addition to the measured value of the floor temperature sensor 11, and is a model for estimating the floor temperature at a certain position. For example, the near-floor temperatures at multiple locations in the perimeter zone P on the north side of a specific target space S on a certain floor are measured using the measured values of the near-floor temperature sensor 11 provided only in the northern perimeter zone P, and other It is estimated based on parameters.

For estimating the temperature near the bed using the temperature estimation model M, the following parameters can be used, for example.
・Outside air temperature (values obtained at multiple heights (e.g., rooftop, high-rise, and low-rise) may be used)
・Wind direction (values obtained at multiple heights (for example, rooftop, high-rise, and low-rise) may be used)
・Wind speed (values obtained at multiple heights (e.g., rooftop, high-rise, and low-rise) may be used)
・Rainfall amount・Insolation amount・Measured value of the near-floor temperature sensor 11 (measured value of the near-floor temperature sensor 11 installed in a different position from the position where you want to estimate the near-floor temperature. Same target space S in FIG. 2) Measured value of the near-floor temperature sensor 11 installed on the side (within the perimeter zone P of the same system)
- Operating status of air conditioner 1 (off/cooling/heating, target value of supply air temperature, supply air amount)
- Operating status of perimeter fan 6 (on/off, air volume)
- Operating status of variable air volume device 5 facing perimeter zone P (on/off, set temperature, required air volume)
・Measurement value of temperature sensor 9 installed in target space S ・Date (at least one of month or day)
・Time (at least one of hours or minutes)
・Day of the week (Sunday, Monday, Tuesday, Wednesday, Thursday, Friday, and Saturday, or holiday or weekday)

As an example of parameter selection for generating a suitable temperature estimation model M, among the above parameters, at least the outside air temperature, the amount of solar radiation, the measured value of the near-floor temperature sensor 11, the measured value of the temperature sensor 9, and the measured value of the perimeter fan 6 are selected. The driving state can be used as a set of features. Alternatively, in addition to the outside air temperature, the amount of solar radiation, the measured value of the near-floor temperature sensor 11, the measured value of the temperature sensor 9, and the operating state of the perimeter fan 6, other parameters may be used.

It should be noted that among the above parameters, the outside air temperature, amount of rainfall, and amount of solar radiation may have a time-delayed influence on the predicted value of the temperature near the floor. Therefore, for these values, actual values measured before the desired time point (for example, about 10 to 30 minutes before) may be used as parameters.

Furthermore, since the environment within the target space S changes greatly depending on the operating state of the perimeter fan 6, the operating state of the perimeter fan 6 is used as a feature when reflecting the operating state of the perimeter fan 6 in the temperature estimation model M. Alternatively, or in addition to using the operating state of the perimeter fan 6 as the feature quantity, the temperature estimation model M may be used depending on the operating state of the perimeter fan 6. That is, for example, a temperature estimation model M when the operating state of the perimeter fan 6 is on (temperature estimation model M is set as _ON ) and a temperature estimation model M when the operating state of the perimeter fan 6 is off (temperature estimation model M is set as _OFF ) are respectively generated. Then, the temperature estimation models M _ON and M _OFF are switched depending on the operating state of the perimeter fan 6.

Further, as each parameter, in place of the parameters exemplified here, equivalent parameters with different units or definitions, or related parameters can be used. Further, in addition to the parameters exemplified above, some other parameter related to the temperature near the bed may be used. Furthermore, it goes without saying that processing such as standardization and centering of feature amounts may be performed as appropriate.

The learning data D is the air conditioning data accumulated in the central monitoring device 12 from the control device 10 of each floor (especially the standard floor) and other sensors (not shown) over an appropriate period (for example, from several days to about one year). This is a set of data related to the operation of the temperature estimator 13 and is stored in the temperature estimator 13. The model generation unit 14 generates a temperature estimation model M based on the learning data D, and stores it in the temperature estimation unit 13. Further, the temperature estimation section 13 includes a correction value calculation section 15. The correction value calculation unit 15 calculates a temperature correction value based on the temperature near the floor at each location in the perimeter zone P of each floor calculated using the temperature estimation model M. The temperature correction value is a correction value that is added to the set temperature for each variable air volume device 5 facing the perimeter zone P. The role of this temperature correction value will be explained again later.

Generation of the temperature estimation model M by the model generation unit 14 will be explained. Various types of models such as linear regression, ridge regression, gradient boosting, and random forest can be adopted as the temperature estimation model M. For example, if the temperature estimation model M is generated using a neural network, the floor Nearby temperature can be estimated with high accuracy. Here, especially when a two-layer linear neural network is used, accurate estimation is possible without overlearning even in a short learning period of about two weeks.

The learning data D used to generate the temperature estimation model M includes various parameters (for example, This is a data set in which parameters such as those exemplified in Figure 1) and actual measured values of the temperature near the bed are recorded. The actual measured value of the near-floor temperature is obtained from near-floor temperature sensors 11 installed at various locations in the perimeter zone P of the reference floor. Further, some of the parameters related to the temperature near the floor can be acquired from the air conditioner 1, the temperature sensor 9, the control unit of the variable air volume device 5, etc.

In the learning data D, in addition to each of the above-mentioned parameters at a plurality of points in time, an actual measured value of the near-floor temperature obtained at the reference floor at each point in time is recorded.

Note that the learning data D may be collected on the condition that, for example, all of the following conditions are met.
・Whether heating operation is being performed. In the perimeter zone P, the problem caused by cold air as described above occurs only when the outside air temperature is low and heating operation is being performed. In other words, it is necessary to estimate the temperature near the floor, calculate a temperature correction value based on it, and perform operation using the temperature correction value only during heating operation. Therefore, only the parameters recorded during the heating operation are used as the learning data D.
- Whether the outside air temperature is lower than a preset threshold value. The above-mentioned problem occurs only when the outside air temperature is lower than the indoor air temperature by a certain degree, so it is necessary to estimate the temperature near the floor and calculate the temperature correction value only when the outside air temperature is low. Therefore, the learning data D is collected only when the outside air temperature is less than the threshold value.
- Whether or not the variable air volume device 5 is in operation. If the variable air volume device 5 itself is not operated, it will naturally not operate using the temperature correction value, so there is no need to estimate the temperature near the floor or calculate the temperature correction value. Therefore, when the variable air volume device 5 is not in operation, the learning data D is not collected.

The model generation unit 14 performs machine learning using the learning data D, and generates a temperature estimation model M that estimates the temperature near the floor at each location in the perimeter zone P on each floor based on various parameters. When generating the temperature estimation model M using a neural network, the model generation unit 14 appropriately selects a plurality of parameters from the various parameters described above recorded in the learning data D, and weights each of them as necessary. and form a pattern of choices. While comparing the near-floor temperature estimated from the formed pattern with the actual near-floor temperature acquired by the near-floor temperature sensor 11 on the reference floor, the process of modifying the pattern is repeated, and machine learning is used to obtain a highly accurate temperature. An estimated model M is finally generated. The generated temperature estimation model M is a model that estimates the temperature near the floor at a certain position from the parameters related to the temperature near the floor in the target air conditioning system.

Note that among the parameters listed above, in order to avoid using the "measured value of the near-floor temperature sensor 11," only a parameter selected from the other parameters may be used as an explanatory variable. . If the near-floor temperature could be estimated with sufficient accuracy without using the measured value of the near-floor temperature sensor 11, there would be no need to install the near-floor temperature sensor 11 in the perimeter zone P of each floor other than the standard floor, and the near-floor temperature could be estimated with sufficient accuracy. The number of installed sensors 11 can be reduced.

In the air conditioning system as described above, an example of a procedure for operating the variable air volume device 5 facing the perimeter zone P using the estimated near-floor temperature and the temperature correction value calculated based on this is shown in FIG. This will be explained with reference to a flowchart.

The temperature estimation unit 13 (see FIG. 3) acquires information regarding the operating status of each part of the air conditioning system through the central monitoring device 12 (step S1). The information acquired here includes, for example, the supply air temperature (temperature of supply air A1) in each air conditioner 1, and the actual measured value of the temperature of indoor air A2 acquired by the temperature sensor 9 installed in the target space S on each floor. , the actual measured value of the temperature near the floor obtained by the near-floor temperature sensor 11 installed in the perimeter zone P of the target space S on each floor, the set temperature in each target space S and the variable air volume device 5, and the air outlet of each variable air volume device 5. These include the air volume (damper opening degree), the outside temperature measured by a temperature sensor (not shown), the date and time, etc. (see FIGS. 1 to 3). Furthermore, the near-floor temperature of each part in the perimeter zone P of each target space S, estimated using the temperature estimation model M, is also acquired in step S1.

Next, based on the acquired information, it is determined whether or not to perform operation using the temperature correction value in the variable air volume device 5 located downstream of each air conditioner 1 constituting the air conditioning system ( Step S2). In this step S2, whether or not the operation can be executed using the temperature correction value is determined based on, for example, whether or not all of the following conditions are satisfied (the conditions listed below are just examples, and other conditions may not be applicable). conditions can also be used).
・Heating operation is being performed. In the perimeter zone P, the problem caused by cold air as described above occurs only when the outside air temperature is low and the heating operation is being performed, so the operation using the temperature correction value is performed only during the heating operation.
- The outside temperature is lower than a preset threshold. The above-mentioned problem occurs only when the outside air temperature is lower than the indoor air temperature to some extent, so the operation using the temperature correction value is performed only when the outside air temperature is less than the threshold value. For example, the threshold value used here is set in two stages, and when changing the temperature correction value from valid to invalid, the higher threshold is used, and when changing from invalid to valid, the lower one is used. It is preferable to use a threshold value of , since excessively frequent switching can be prevented.

After determining whether or not to use a temperature correction value for each air conditioner 1, for each individual air conditioner 1, check whether or not a temperature correction value is used in each variable air volume device 5 downstream of the air conditioner 1, and the specific numerical value. I will set it up. First, in step S3, it is determined whether or not it was determined in the previous step S2 that one air conditioner 1 should be operated using the temperature correction value in the variable air volume device 5 on the downstream side. .

Regarding the target air conditioner 1, if any downstream variable air volume device 5 does not operate using the temperature correction value, the temperature correction value will not be used for each variable air volume device 5 downstream of the air conditioner 1. Make settings. In step S4, one variable air volume device 5 is set not to use the temperature correction value (temperature correction value=0). In the next step S5, it is determined whether or not there is any variable air volume device 5 located downstream of the target air conditioner 1 for which the temperature correction value has not been set. If there is an unset variable air volume device 5, the process moves to another variable air volume device 5 (step S6), and the temperature correction value is set to 0 for that variable air volume device 5 (step S4). After repeating this process and setting temperature correction values for all variable air volume devices 5 downstream of the target air conditioner 1, the process moves to step S7.

In step S7, the upper limit value of the supply air temperature is set for the target air conditioner 1. The upper limit value of the supply air temperature in the air conditioner 1 is set by the central monitoring device 12, and normally the set value in this central monitoring device 12 can be used as is, but in this embodiment, the upper limit value is set by the central monitoring device 12. Change settings only in specific cases. The change in the upper limit value of the supply air temperature will be explained later when explaining step S16, but in step S7, it is assumed that the upper limit value is the same as the setting value in the central monitoring device 12. After step S7 is completed, the process moves to step S17, which will be described later.

If it is determined in step S3 that at least some of the variable air volume devices 5 downstream of the target air conditioner 1 have been determined to operate using the temperature correction value, the process moves to step S8. In this step S8, it is determined individually whether or not to effectively set the temperature correction value for each variable air volume device 5 located downstream of the target air conditioner 1. The determination in step S3 is made, for example, based on whether all of the following conditions are satisfied.
・There is no failure in the variable air volume device 5.
- The operation of the applicable variable air volume device 5 is turned on.

After determining whether the temperature correction value is valid or invalid for each variable air volume device 5, the process advances to step S9. In step S9, it is determined whether or not the operation based on the temperature correction value was effectively set in the previous step S8 for one variable air volume device 5. If the temperature correction value of the variable air volume device 5 has been set to be invalidated, the process proceeds to step S10, and the temperature correction value is set to 0 for the variable air volume device 5. If it is determined in step S9 that the temperature correction value has been set to be valid for the variable air volume device 5 in question, the process proceeds to step S11, where a temperature correction value is calculated.

The calculation of this temperature correction value will be explained below, but first the significance of the temperature correction value will be explained. As mentioned above, the temperature correction value is a correction value that is added to the set temperature for each variable air volume device 5 facing the perimeter zone P, but this is because the installation position of the temperature sensor 9 is on the floor. This is due to the fact that it is located away from the surface, and is set to correct the difference between the measured temperature and the sensible temperature that occurs due to this. In the air conditioning system shown in FIG. 1, the actual measured value of the indoor air A2 is grasped as the measured value of the temperature sensor 9 provided at the height of the ceiling 3. On the other hand, in the target space S, the person is located near the floor surface, so as explained above, especially in the perimeter zone P, the perceived temperature of the person and the measured value of the temperature sensor 9 are measured. Discrepancies in temperature tend to occur.

During heating, the air conditioning system composed of the control device 10, the air conditioner 1, and the variable air volume device 5 sets the measured value of the temperature sensor 9 (ceiling temperature PV ₁ as 1) to the set value (indoor temperature set value SP ₁₎ . ), each device is operated so that the ceiling temperature _PV1 approaches the indoor temperature set value _SP1 . However, the actual temperature of the indoor air A2 near the floor (referred to as the estimated floor temperature _PV2 ) is often lower than the ceiling temperature _PV1 . Therefore, even if the ceiling temperature PV ₁ becomes sufficiently close to the indoor temperature set value SP ₁ , there is a difference between the estimated floor temperature PV ₂ and the ceiling temperature PV ₁ , and as a result, for people near the floor, A situation may arise in which satisfactory warmth cannot be obtained. In order to correct this, first calculate the estimated floor temperature value _PV2 (step S1), and then calculate the temperature correction value (denoted as β) according to the deviation between this value and the indoor temperature set value _SP1. , a set temperature value that takes this into consideration is set in each variable air volume device 5 (step S11). As a result, the temperature correction value β is added to the set value related to the temperature of the indoor air A2 near the ceiling 3 (indoor temperature set value SP ₁ ), and each device is operated with this as the target value. temperature situation is corrected.

Management of the temperature near the bed using such a temperature correction value β can also be explained using a diagram as shown in FIG. 6, for example. In FIG. 6, the vertical line on the left indicates the temperature near the floor, and the vertical line on the right indicates the temperature near the ceiling. For example, if the indoor temperature set value SP ₁ is 23°C, and the air conditioning system is operated based on this, the ceiling temperature PV ₁ is 23°C. , the temperature near the bed is, for example, 20°C. Since this is lower than the set value, 3°C is added to the indoor temperature set value _SP1 as a temperature correction value β, and the set value is raised to 26°C on the ceiling side. As a result, the temperature difference near the floor surface is compensated for, resulting in a comfortable temperature (23° C.).

However, the temperature difference here is not uniform and may change depending on the conditions. For example, if sunlight enters the perimeter zone P, the floor surface will be warmed and the temperature difference will be reduced. At this time, if the temperature correction value β is set uniformly (for example, 3°C) without using the deviation between the estimated floor temperature value PV ₂ and the indoor temperature set value SP ₁ as described above, the temperature near the floor will actually increase. It goes up too high. Conversely, there may be a case where the temperature difference is large and the temperature near the floor is insufficient even if the temperature correction value β is added to the set value. Therefore, as explained above, if the temperature correction value β is calculated each time based on the deviation between the estimated floor temperature value PV ₂ and the room temperature set value SP ₁ , the temperature situation near the floor surface can be suitably maintained. can. In other words, instead of uniformly setting the temperature correction value to the set value, the temperature correction value can be adjusted according to the temperature situation near the floor surface.

An example of a procedure for calculating the temperature correction value β by the correction value calculation unit 15 will be described. First, the control deviation (assumed to be _E2 ), which is the basis for the temperature correction value β, is calculated using the following formula.
[Number 1]
Control deviation E ₂ = Indoor temperature set value SP ₁ - Estimated temperature near the floor PV ₂ ......(1)
Indoor temperature set value SP ₁ = Center set value SP _C +k・α−γ ...(2)

The control deviation E ₂ is the deviation between the room temperature set value SP ₁ and the estimated floor temperature value PV ₂ , and the air conditioning system is operated in a direction to eliminate this deviation.

The room temperature set value SP ₁ can be calculated based on the central set value SP _C and other values, as shown in equation (2). The central set value SP _C is a set temperature value in the variable air volume device 5 determined by the central monitoring device 12. α is a correction value added to the set temperature in the variable air volume device 5 by an operation by a person in the target space S, and can take, for example, two values of 0 and 1 (initial value is 1). k is a coefficient that determines the weighting of α when calculating the control deviation _E2 . γ is a value set as a temperature dead zone for switching between cooling and heating.

After calculating the control deviation E ₂ , the effective control deviation E _2eff is determined, for example, using the relationship shown in the following formula.
[Number 2]
E _2eff = E ₂ + δ (E ₂ ≦-δ)
E _2eff = 0 (-δ<E ₂ <δ)
E _2eff = E ₂ - δ (δ≦E ₂ )

In other words, centering on the point E ₂ = 0, in the range -δ<E ₂ <δ, E _2eff = 0, and in other ranges, that is, the range where the absolute value of the control deviation E ₂ is greater than or equal to the threshold (δ). In this step, the effective control deviation _E2eff is calculated linearly according to the increase or decrease in the control deviation _E2 . This is effective in preventing frequent switching of operating states in a range where the absolute value of the control deviation _E2 is small.

Using the thus obtained effective control deviation _E2eff as a variable, the temperature correction value is determined based on the relationship shown in FIG. 7, for example. The example shown here uses PI control, and when the effective control deviation _E2eff is 0°C or higher, temperature correction is performed so that it is proportional to the effective control deviation _E2eff (in the case of the example shown, proportional coefficient = 1). I am trying to determine the value. If the estimated temperature near the floor is lower than the set value determined by the central monitoring device 12, a temperature correction value is added to the set temperature in the variable air volume device 5 at the corresponding position to increase the set temperature, and the air outlet It increases the amount.

In the example shown here, the upper limit of the temperature correction value is set to +3°C, and if the effective control deviation _E2eff is 3°C or more, the temperature correction value is uniformly +3°C. Note that the formula for calculating the control deviation _E2 or the effective control deviation _E2eff shown in Equation 1 above and the relationship between the effective control deviation _E2eff and the temperature correction value shown in FIG. 7 are just examples, and other variables may be used. The control deviation E ₂ , the effective control deviation E _2eff , and the temperature correction value β may be determined by taking into account or using a relationship different from Equation 1 or the example of FIG.

After setting the temperature correction value for the target variable air volume device 5 (steps S10, S11), the process proceeds to step S12. In step S12, it is determined whether there is a variable air volume device 5 downstream of the air conditioner 1 currently being targeted, for which the temperature correction value has not yet been set. If there is a variable air volume device 5 that has not been set yet, the target is moved to another variable air volume device 5 (step S13), and a temperature correction value is set for that variable air volume device 5 (steps S9 to S11).

Once the temperature correction values have been set for all variable air volume devices 5 downstream of the target air conditioner 1, the process proceeds to step S14. In step S14, it is determined again whether or not any of the variable air volume devices 5 downstream of the target air conditioner 1 is currently operating with the temperature correction value enabled. If the determination is NO here, the process advances to step S15. In step S15, the upper limit value of the supply air temperature of the target air conditioner 1 is set to be the same as the set value in the central monitoring device 12.

If the determination in step S14 is YES, that is, if there is a variable air volume device 5 downstream of the target air conditioner 1 that is operating with the temperature correction value enabled, the process proceeds to step S16. In step S16, an upper limit value of the supply air temperature is set for the target air conditioner 1, separately from the set value in the central monitoring device 12.

As mentioned above, the problem of cold draft in the perimeter zone P occurs when the outside air temperature is low. Therefore, in this embodiment, temperature correction is performed with the outside air temperature being lower than the threshold value as one of the conditions. I try to operate using values. On the other hand, in the air conditioning system shown in FIGS. 1 to 3, the amount of heat supplied to the target space S is determined by the amount of air blown from each variable air volume device 5 and the temperature of the air supplied from the air conditioner 1. That is, if the supply air temperature in the air conditioner 1 is high, the amount of air blown out for supplying the same amount of heat will decrease accordingly. If the amount of air blown from the variable air volume device 5 facing the perimeter zone P becomes smaller, a temperature distribution will occur in the air in the perimeter zone P, increasing the possibility that a cold draft will occur.

Therefore, when operating using the temperature correction value, in step S16, the upper limit value of the supply air temperature is set based on the outside air temperature based on the relationship shown in FIG. 8, for example. In the example shown here, when the outside air temperature is 10° C. or lower, the upper limit value of the supply air temperature is lowered. When the outside air temperature is in the range of 10°C or lower and 0°C or higher, the supply air temperature is linearly lowered in response to changes in outside air temperature (in the case of Figure 8, proportionality coefficient = 0.6); In this case, the upper limit value of the supply air temperature is uniformly set to 25°C. In this way, when the outside air temperature is low, the supply air temperature can be prevented from rising too much, and the air volume blown from the variable air volume device 5 facing the perimeter zone P can be ensured. Incidentally, since the determination that the outside air temperature is lower than the threshold value has already been made in the previous step S2, it is sufficient to specifically set the upper limit value of the supply air temperature in this step S16.

After setting the upper limit value of the supply air temperature (step S7, S15 or S16), the process moves to step S17. In step S17, it is determined whether or not there remains any air conditioner 1 whose operation using the temperature correction value has not been set for the downstream variable air volume device 5. If it remains, move the target to another air conditioner 1 (step S18), set the operation using the temperature correction value for the variable air volume device 5 downstream thereof, and set the upper limit value of the supply air temperature (step S18). S3-S16). After setting the downstream variable air volume device 5 and setting the upper limit value of the supply air temperature for all air conditioners 1, the process moves to step S19. In step S19, the settings related to the driving conditions determined in steps S2 to S18 are input to the central monitoring device 12. The central monitoring device 12 operates each part of the air conditioning system based on the recorded settings.

In this way, in the air conditioning system of this embodiment, the near-floor temperature at each position in the perimeter zone P is estimated, and if the estimated near-floor temperature for a certain position is low, the variable air volume device 5 facing that position is A temperature correction value is added to the set temperature (step S11), and the set temperature is raised to perform operation. In the variable air volume device 5, the volume of air blown is adjusted appropriately according to the raised set temperature, and the volume of air blown from the air outlet 4 to the perimeter zone P is increased. Furthermore, when the outside air temperature is low, the upper limit value of the air supply temperature from the air conditioner 1 is lowered (step S16) to ensure the amount of air blown from the variable air volume device 5. As a result, the indoor air A2 (see FIG. 1) supplied from the variable air volume device 5 reaches the vicinity of the floor surface and the perimeter fan 6. In this way, the temperature distribution near the floor surface is corrected, as shown in FIG. 9, based on the estimated value of the near-floor temperature. That is, the warm air (indoor air A2) that has reached the perimeter fan 6 from the variable air volume device 5 is sent to the upper suction port 16 and taken in as exhaust air A4, thereby forming an upward flow of warm air, which causes the perimeter zone P The cold air generated at the outermost periphery is blocked and cold drafts are prevented from entering the inside. Then, in the perimeter zone P and the interior zone I located inside the perimeter zone, the warm air is filled to the vicinity of the floor surface, and a suitable air-conditioning condition is realized.

Such control can be carried out, for example, by providing near-floor temperature sensors 11 at positions corresponding to all of the variable air volume devices 5 located near the perimeter zone P, as shown in FIG. This can be done by actually measuring the temperature near the floor at each location. However, if the near-floor temperature sensors 11 are installed throughout the perimeter zone P on each floor of a building, the number of near-floor temperature sensors 11 will be enormous, which will increase the installation cost and make management troublesome. In this embodiment, by estimating the temperature near the floor in the perimeter zone P using software, it is possible to control the amount of air blown from the variable air volume device 5 based on the temperature near the floor while reducing the cost of installing the sensor. .

Here, as explained above, this embodiment employs a control method using a temperature correction value, but such a control method can be understood as a concept as shown in the block diagram in FIG. 10, for example. I can do it. First, in the variable air volume type air conditioning system (see Figure 1), the direct control target is the temperature of indoor air A2 near the ceiling 3 (shown as block B1 in Figure 10); It is grasped as a measured value of the temperature sensor 9 (block B2). This measured value is compared with the target value (block B3) (block B4), the deviation between them (control deviation) is calculated, and the variable air volume device 5 (block B5) is operated to eliminate this control deviation. adjusts the damper opening degree (block B6), thereby adjusting the supply amount of indoor air A2.

In addition, in the air conditioner 1 (block B7) that supplies the air conditioned supply air A1 to the variable air volume device 5 (block B5), the air volume of the fan (block B8) is adjusted according to the required air volume of the variable air volume device 5, Supply air A1 with an appropriate air volume is sent to the downstream variable air volume device 5 (block B6). Additionally, in the air conditioner 1 (block B7), the opening degree of the refrigerant flow path (block B9) is adjusted by load reset control, and the temperature of the supply air A1 is adjusted.

In this way, the temperature of indoor air A2 (block B1), which is the control target, is adjusted through the air volume and temperature of supply air A1. The temperature of the indoor air A2 (block B1) is further influenced by disturbances (block B10), and the resulting temperature of the indoor air A2 (block B1) is grasped by the temperature sensor 9 (block B2) and set to the target value. (Block B3) is compared with (Block B4), and control is performed in a direction that also eliminates fluctuations due to disturbance.

The control method using the temperature correction value creates another loop (minor loop, shown as a region surrounded by a broken line in FIG. 10) formed by blocks B1 to B10. It can be said that this is a cascade control in which a loop outside the area enclosed by the broken line (which is assumed to be a major loop) is added.

That is, the temperature near the floor (block C1) is set as another control target related to the temperature of indoor air A2 near the ceiling 3 (block B1), and this is estimated using the temperature estimation model M, and the output The estimated near-bed temperature value (block C2) is compared with the target value (block C3) (block C4). Then, the temperature correction value (block C5) calculated based on the control deviation is added to the target value set in block B3. In the minor loop, the temperature of the indoor air A2 near the ceiling 3 (block B1) is adjusted based on the target value (block B3) that takes into account the temperature correction value, and as a result, the temperature of the indoor air A2 near the floor ( Block C1) is adjusted. The temperature of the indoor air A2 near the floor (block C1) is also affected by the disturbance (block C6), but control using a major loop that includes a minor loop is effective against this disturbance (block C6) by PI control via the temperature correction value. ). That is, when a disturbance (block C6) occurs due to a change in the outer skin load, the estimated value of the temperature near the floor (block C2) changes, which causes a deviation from the target value of the temperature near the floor (block C3), and cancels that deviation. In the direction, the temperature correction value as the manipulated variable changes and is input into the minor loop.

With this type of control method, the temperature correction value based on the temperature near the floor can be added to the target value of the set temperature without making any changes to the system (minor loop) that has been established as a variable air volume type air conditioning system. Therefore, the temperature situation near the floor surface can be suitably corrected.

Furthermore, such cascade control has an advantage in terms of controllability. If a control configuration is adopted that eliminates the disturbance (blocks B10 and C6) using one loop, the control cycle will be The cycle is at least 5 minutes, and the deviation calculated during the loop becomes large. Therefore, as in this embodiment, a cascade control is configured, which consists of a minor loop that controls the air volume of the variable air volume device 5 and the supply air temperature of the air conditioner 1, and a major loop that controls the estimated near-floor temperature outside of the minor loop. . The control period of the major loop is about 5 minutes, but the control period of the minor loop is several seconds to several tens of seconds, and the deviation calculated in block B4 is small. Since the disturbance input to the minor loop (block B10) is controlled within the minor loop, its influence on the control variables of the major loop is small. In this way, the influence of disturbances can be effectively suppressed and controllability can be improved.

Note that the system configuration of the air conditioning system, the procedure for generating the temperature estimation model M, estimating the temperature near the floor, calculating the temperature correction value, etc. described here are merely examples. As long as the temperature estimation model M can be generated from the above-mentioned various parameters related to the temperature near the floor, the temperature near the floor can be estimated using this model, and the operation of the variable air volume device 5 can be adjusted, the system configuration and various procedures can be adjusted. etc. can be changed in various ways.

For example, in the present embodiment, the floor temperature sensor 11 is provided near the floor at a height of 0 cm or more and less than 10 cm, and the temperature of the air at this height is estimated as the floor temperature. However, the temperature of the air in the living area of 10 cm or more and 170 cm or less may be estimated as the temperature near the floor. In that case, the near-floor temperature sensor 11 may be installed at a height range of 10 cm to 170 cm such as a wall surface, and the temperature at that height may be directly measured, or the near-floor temperature sensor 11 may be installed at a height of 0 cm or more and less than 10 cm. The sensor 11 may be installed, and the temperature at the desired height may be determined by dividing the difference based on the measured value by the ceiling temperature sensor 9 and the measured value by the near-floor temperature sensor 11, for example, by the distance between the two sensors. .

In addition, here, a configuration in which the temperature estimating unit 13 is connected to the central monitoring device 12 and the model generating unit 14 is connected to the temperature estimating unit 13 is illustrated, but the connection relationship between each device constituting the system may be changed as appropriate. obtain. In addition to controlling the operating status of each variable air volume device 5 via the central monitoring device 12, for example, the temperature correction value may be directly set for each variable air volume device 5 from the temperature estimation unit 13. Furthermore, instead of correcting the set temperature, the blowing air volume may be directly corrected.

In addition, when controlling the air volume blown from the variable air volume device 5, the temperature of air supplied from the air conditioner 1, and the operating status of other parts, other factors not explained above may be taken into consideration as appropriate. Of course.

As described above, the air conditioning system of the present embodiment includes the air conditioner 1 that sends out the air supply A1, the air supply duct 2 that guides the air supply A1 from the air conditioner 1 to the target space S, and the air conditioner 1 that supplies the air supply A1 to the target space S. an air outlet 4 that blows out air, a variable air volume device 5 that adjusts the air volume of the supply air A1 blown out from the air outlet 4, a perimeter fan 6 that is provided in the perimeter zone P and that sends indoor air A2 upward, and a perimeter fan 6 that blows out indoor air A2 upward. Based on a plurality of parameters related to the temperature near the floor of the perimeter zone P, the temperature near the floor is estimated at each position of the perimeter zone P, and the temperature near the floor is adjusted to the estimated temperature near the floor. Based on this, the air volume of the variable air volume device 5 facing the perimeter zone P is adjusted. In this way, the amount of air blown from the air outlet 4 to the perimeter zone P is increased appropriately based on the temperature near the floor, and the supplied warm air reaches the perimeter fan 6 and is sent to the upper suction port 16. This blocks the cold air generated at the outermost periphery of the perimeter zone P, and prevents cold drafts from entering inside. In this way, the temperature distribution near the floor surface of the target space S can be corrected. Further, since the temperature near the floor is estimated by software, the amount of air blown from the variable air amount device 5 can be controlled while reducing the cost of installing the sensor.

Further, the air conditioning system of this embodiment is configured to estimate the temperature near the floor of the perimeter zone P using the temperature estimation model M generated by machine learning. In this way, the temperature near the floor of the perimeter zone P can be estimated with high accuracy.

Furthermore, in the air conditioning system of this embodiment, the temperature estimation model M can be generated using a neural network.

Furthermore, in the air conditioning system of this embodiment, the temperature estimation model M can be configured to estimate the floor temperature using some or all of the parameters selected from the following parameters as explanatory variables.
・Outside temperature, wind direction, wind speed, rainfall amount, solar radiation amount, measured value of the near-floor temperature sensor 11 ・Operating state of the air conditioner 1 ・Operating state of the perimeter fan 6 ・Operating state of the variable air volume device 5 facing the perimeter zone P・Measurement value of temperature sensor 9 installed in target space S, date, time, day of week

Further, in the air conditioning system of this embodiment, at least the outside air temperature, the amount of solar radiation, the measured value of the near-floor temperature sensor 11, the measured value of the temperature sensor 9, and the operating state of the perimeter fan 6 can be used as explanatory variables.

Further, in the air conditioning system of this embodiment, the amount of air blown from the variable air volume device 5 is adjusted by adding a temperature correction value to the set temperature in the variable air volume device 5.

Further, in the air conditioning system of this embodiment, the temperature correction value is configured to be adjustable based on the deviation between the estimated near-floor temperature and the set temperature in the variable air volume device 5.

Furthermore, in the air conditioning system of this embodiment, the temperature correction value can be determined using PI control.

Further, the air conditioning system of this embodiment is configured to add a temperature correction value to the set temperature in the variable air volume device 5 facing the perimeter zone P when the outside air temperature is lower than a threshold value. In this way, the amount of air blown by the variable air amount device 5 can be increased in accordance with the raised set temperature.

Further, the air conditioning system of this embodiment is configured to lower the upper limit of the supply air temperature in the air conditioner 1 when the outside air temperature is lower than a threshold value. In this way, when the outside air temperature is low, the supply air temperature can be prevented from rising too much, and the air volume blown from the variable air volume device 5 facing the perimeter zone P can be ensured.

Therefore, according to the present embodiment, the air temperature distribution in the perimeter zone can be suitably corrected.

It should be noted that the air conditioning system of the present invention is not limited to the above-described embodiments, and it goes without saying that various changes can be made without departing from the gist of the present invention.

1 Air conditioner 2 Air supply duct 4 Outlet 5 Variable air volume device 6 Perimeter fan 9 Temperature sensor 11 Near-floor temperature sensor 16 Inlet A1 Air supply A2 Indoor air M Temperature estimation model P Perimeter zone S Target space

Claims (10)

An air conditioner that sends out air supply,
an air supply duct that guides air supply from the air conditioner to the target space;
An air outlet that blows out air into the target space;
a variable air volume device that adjusts the air volume of the supply air blown out from the air outlet;
A perimeter fan that is installed in the perimeter zone and sends indoor air upward;
and a suction port provided above the perimeter fan,
Measuring at least part of the temperature near the floor from indoor air near the floor taken into the perimeter fan,
A temperature estimation model generated by machine learning is used to calculate the temperature near the floor at each position in the perimeter zone based on the parameter that is the temperature near the floor of at least some of the parameters and the parameter related to the temperature near the floor in the perimeter zone. An air conditioning system characterized in that the air conditioning system is configured to adjust the amount of air blown from the variable air amount device facing the perimeter zone based on the estimated near-floor temperature. The temperature estimation model is a model that is generated based on learning data and estimates the temperature near the floor using various parameters as explanatory variables,
2. The learning data is a data set in which a plurality of parameters related to the temperature near the floor and an actual measured value of the temperature near the floor when the air conditioning system is actually operated are recorded. air conditioning system. The air conditioning system according to claim 2, wherein the temperature estimation model is generated using a neural network. Equipped with a near-floor temperature sensor that measures the temperature near the floor from indoor air near the floor.
4. The temperature estimation model according to claim 2, wherein the temperature estimation model is configured to estimate the temperature near the bed using some or all of the parameters selected from the following parameters as explanatory variables. Air conditioning system.
・Outside temperature, wind direction, wind speed, rainfall amount, solar radiation amount, measured value of the temperature sensor near the floor, operating status of the air conditioner, operating status of the perimeter fan, operating status of the variable air volume device facing the perimeter zone, Measured values, date, time, and day of the week of the temperature sensor installed in the target space 5. The air conditioning system according to claim 4, wherein at least outside air temperature, solar radiation, a measured value of the near-floor temperature sensor, a measured value of the temperature sensor, and an operating state of the perimeter fan are used as explanatory variables. Any one of claims 1 to 5, wherein the adjustment of the air volume of the variable air volume device based on the estimated temperature near the floor is performed by adding a temperature correction value to the set temperature of the variable air volume device. The air conditioning system described in paragraph 1. 7. The air conditioning system according to claim 6, wherein the temperature correction value can be adjusted based on a deviation between the estimated near-floor temperature and the set temperature in the variable air volume device. The air conditioning system according to claim 7, wherein the temperature correction value is determined using PI control. Any one of claims 6 to 8, characterized in that, when the outside air temperature is lower than a threshold value, the temperature correction value is added to the set temperature in the variable air volume device facing the perimeter zone. The air conditioning system described in paragraph 1. The air conditioning system according to any one of claims 6 to 9, characterized in that the air conditioning system is configured to lower the upper limit value of the supply air temperature in the air conditioner when the outside air temperature is lower than a threshold value.

Images