Computerized apparatus and computer-implemented method for controlling an HVAC system

Abstract

A computerized device for controlling an HVAC system of a room comprises a providing unit for providing a metamodel for modeling the distribution of a plurality of physical quantities of the air in the room, the metamodel being based on reduced-order modeling of a plurality of performed simulations of the physical quantities for a specific room configuration of the room, and a determining unit for determining at least one value of a specific physical quantity of the plurality of physical quantities at a specific location in the room using the provided metamodel and a plurality of measured values ​​of the specific physical quantity measured by a plurality of physical sensors. Furthermore, a system having such a computerized device, a computer-implemented method and a computer program product are proposed.

Description

Technical Field

[0001] The invention relates to a computerized device for controlling an HVAC system (HVAC: Heating, Ventilation and Air Conditioning). The invention also relates to an HVAC system comprising such a computerized device for controlling an HVAC system. Furthermore, the invention relates to a computer-implemented method and a computer program product for controlling an HVAC system. Background Art

[0002] Today, the HVAC industry is a rapidly developing technological field that follows the common trend of digitalization by adopting the IoT concept (IoT: Internet of Things) that connects various smart devices and sensors within a single ecosystem. In particular, quality control of such HVAC systems is performed in order to comply with existing standards and provide appropriate spaces for people or institutions, which quality control usually involves the analysis of temperature, the removal of moisture, smoke, heat, dust, carbon dioxide and other gases.

[0003] To provide technical solutions, different manufacturers use intelligent control devices to ensure the highest level of comfort. In particular, the so-called "Perfect Place" concept combines the use of IoT devices, smart sensors and cloud technology to solve such challenging tasks.

[0004] However, it may be mentioned that conventional solutions have a certain technical problem, which significantly reduces the efficiency and customization capabilities. In particular, the control of such conventional systems is performed based on information from physical sensors placed at respective predefined locations in the room. Usually the respective locations are chosen to take into account specific room characteristics, which increases the reliability of the sensor indications. However, considering that the sensors may be difficult to place at room locations where people usually live, there is no guarantee that the data from the respective physical sensors match the specific conditions, making the room less comfortable.

[0005] For example, in a room where the physical sensors are located at defined locations, the physical sensors may sense a temperature of 24°C, where in important areas of the room, the temperature may be much lower, and therefore, conventional systems cannot guarantee the desired temperature for people in the room far from the physical sensors. Increasing the number of physical sensors in a room may improve the predictive capabilities of the HVAC system. However, this increases the overall cost of such an HVAC system and the difficulty of the setup process.

[0006] It can be noted that the control of the HVAC system can be done in several ways:

[0007] The most direct method is to manually apply the desired settings to the HVAC system, either using a remote control or a direct app. In this case, no physical sensors are implemented outside the device.

[0008] A more sophisticated approach implies the use of smart sensors, such as the Siemens Smart Thermostat RDS120. In this case, the desired temperature is set for the device manually or using a remote control, the current temperature measured by at least one physical sensor is compared to the input temperature, and the HVAC system operating paradigm is set according to a specific algorithm designed to match the current sensor temperature to the desired value. It is worth noting that the Siemens Smart Thermostat includes several indoor air quality sensors that act similarly to the desired temperature sensors, such as relative humidity sensors or VOC and CO2 sensors.

[0009] However, despite the ability to control the performance of the HVAC system based on sensor measurements, the above approach imposes several restrictions on the sensor location. According to the user manual of the Siemens Smart Thermostat RDS120, only a few locations meet the requirements for sensor placement. Here, it is worth mentioning that the appropriate locations are quite far away from potential human locations, so this concept may not be able to solve the above problems. Summary of the invention

[0010] It is therefore an object of the present invention to enhance the control of an HVAC system.

[0011] According to a first aspect, a computerized device for controlling an HVAC system of a room is proposed. The computerized device comprises:

[0012] A unit is provided for providing a metamodel for modeling the distribution of multiple physical quantities of the air in a room, wherein the metamodel is based on reduced order modeling (ROM) of multiple performed simulations of the physical quantities of a specific room configuration of the room, and a determination unit is provided for determining at least one value of a specific physical quantity among the multiple physical quantities at a specific position in the room using the provided metamodel and multiple measurement values ​​of the specific physical quantity measured by multiple physical sensors.

[0013] In particular, a plurality of physical sensors are arranged in or near the room and are located at a position different from the specific position. For example, the plurality of physical quantities include air temperature, air speed, relative humidity, absolute humidity and / or CO2 content of the air. The physical quantity of the air can also be referred to as air property.

[0014] A computerized device may also be referred to as a control system, a control device or a controller. In particular, the computerized device may be an intelligent controller.

[0015] The computerized device improves the accuracy of the prediction of the air properties in a room, in particular at any location in the room. This means that the computerized device is suitable for determining the air properties, such as temperature, at those locations where there are no physical sensors. Therefore, the performance of the entire HVAC system is improved.

[0016] In particular, by using the present metamodel, the computerized device takes into account the characteristics of any specific space in the room, allowing the application of the perfect place concept by achieving more comfortable environmental conditions for people at each position in the room. In addition, the current metamodel-based control system has less stringent requirements on the location of physical sensors. Therefore, the installation process is significantly simplified.

[0017] An additional advantage is that the metamodel requires much less computing power than CAE simulations, so it can be directly embedded in computerized devices (e.g. intelligent controllers).

[0018] In the following, several embodiments of a computerized device for controlling an HVAC system are described.

[0019] According to a further embodiment, the metamodel models the 3D distribution of multiple physical quantities of the air in the room. In this embodiment, the metamodel may model the distribution of all the above physical quantities or any subset thereof.

[0020] According to a further embodiment, the plurality of performed simulations comprises a CAE simulation (CAE: Computer Aided Engineering) applied to a specific room configuration. In particular, an accurate CAE model can be built for any geometry of the room.

[0021] In particular, appropriate orthogonal decomposition and / or Krylov subspace methods may be applied to construct the meta-model.

[0022] According to another embodiment, the room configuration describes the geometry of the room, in particular including the area of ​​the room, the height of the room, the windows of the room and the doors of the room, the position of the room in the building, the number of people in the room, the positions of the people in the room, the objects in the room and / or the positions of the objects in the room.

[0023] According to a further embodiment, reduced order modeling comprises machine learning (ROM: Reduced Order Modeling).

[0024] According to further embodiments, reduced order modeling includes simulations and / or a plurality of empirical models.

[0025] According to further embodiments, simulations are performed for a plurality of locations in a room, wherein each simulation is performed based on a set of boundary conditions.

[0026] According to a further embodiment, the determination unit is configured to determine the value of the specific physical quantity at any location in the room.

[0027] According to a further embodiment, the meta-model is constructed based on multiple parameter simulations which are approximated as a set of algebraic equations for a set of desired physical quantities using reduced order modeling, in particular using machine learning.

[0028] According to a further embodiment, the set of algebraic equations is formed as a system of linear equations, wherein the column vector of the desired physical quantity is equal to the sum of the column vectors of products and differences of the matrix describing the measured values ​​of the physical quantity and the column vectors of the metamodel coefficients.

[0029] An example of such a system of linear equations is shown below:

[0030]

[0031] In the linear equation system, the column vector y represents the desired physical quantity. In the matrix, x represents the measured value of the physical quantity, the column vector β represents the metamodel coefficients, and the column vector ε represents the difference.

[0032] According to a further embodiment, the computerized device comprises:

[0033] a receiving unit for receiving a request defining a desired temperature at a desired location in the room, and

[0034] A generating unit is configured to generate a control signal for controlling the HVAC system based on at least one value of the specific physical quantity determined by the determining unit and the received request.

[0035] For example, the receiving unit may be coupled to a remote controller to which the user may enter his request to define a desired temperature, in particular his position in the room. This request may then be transmitted to the receiving unit of the computerized device. The providing unit then provides control signals for controlling the HVAC system based on the request received from the user.

[0036] Each unit, such as a providing unit or a determining unit, can be implemented in hardware and / or software. If the unit is implemented in hardware, it can be embodied as a device, such as a computer or a processor or a part of a system (such as a computer system). If the unit is implemented in software, it can be embodied as a computer program product, a function, a routine, a program code or an executable object.

[0037] In particular, the computerized device may be a computer. Furthermore, the computerized device may be or may comprise a computer-aided or computer-related system or a computer system.

[0038] According to a second aspect, a HVAC system is provided, comprising a computerized device of the first aspect or an embodiment of the first aspect and a plurality of fan coil units for conditioning at least one property of air in a room, the fan coil units being controlled by the computerized device.

[0039] A user may directly or remotely input a request for a specific temperature at a specific location in a room, and the HVAC system may adjust that temperature by controlling the fan coil unit.

[0040] According to a third aspect, a computer-implemented method for controlling an HVAC system of a room is provided. The method comprises:

[0041] A metamodel is provided for modeling the distribution of multiple physical quantities of the air in a room, the metamodel being based on reduced-order modeling of multiple performed simulations of the physical quantities for a specific room configuration of the room, and determining at least one value of a specific physical quantity among the multiple physical quantities at a specific location in the room using the provided metamodel and multiple measurement values ​​of the specific physical quantity measured by multiple physical sensors.

[0042] Embodiments and features according to the first aspect are also embodiments of the third aspect.

[0043] According to a fourth aspect, a computer program product is provided, wherein the computer program product comprises a program code, and when the program code is run on at least one computer, the program code is used to perform the method of the third aspect.

[0044] A computer program product such as a computer program means may be embodied as a memory card, USB stick, CD-ROM, DVD or a file downloadable from a server in a network. For example, such a file may be provided by transmitting a file comprising the computer program product from a wireless communication network.

[0045] Other possible implementations or alternative solutions of the present invention also include combinations of features described above or below with respect to the embodiments (not explicitly mentioned here). Those skilled in the art can also add individual or isolated aspects and features to the most basic form of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Further embodiments, features and advantages of the present invention will become apparent from the following description and dependent claims, taken in conjunction with the accompanying drawings, in which:

[0047] Figure 1 A schematic block diagram of a first embodiment of a computerized device for controlling an HVAC system of a room is shown;

[0048] Figure 2 A schematic block diagram of a second embodiment of a computerized device for controlling an HVAC system of a room is shown;

[0049] Figure 3 A schematic diagram illustrating an example of a room including an HVAC system and a computerized device for controlling the HVAC system is shown;

[0050] Figure 4 A sequence of method steps of a first embodiment of a method for controlling an HVAC system of a room is shown; and

[0051] Figure 5 A sequence of method steps of a second embodiment of a method for controlling an HVAC system of a room is shown.

[0052] In the drawings, like reference numbers indicate identical or functionally equivalent elements unless otherwise indicated. DETAILED DESCRIPTION

[0053] Figure 1 A schematic block diagram of a first embodiment of a computerized device 100 for controlling an HVAC system 10 of a room 1 is depicted.

[0054] exist Figure 3 The following table shows the Figure 1 Example of an HVAC system 10 and computerized equipment 100 for room 1. Figure 3 The schematic diagram of room 1 shows that room 1 has door 2, two windows 3, 4 and table as an example of objects. Of course, such room 1 can have any other room configuration, including any number of doors 2, any number of windows 3, 4 and any number of objects 5.

[0055] In addition, Figure 3 In room 1, there are Figure 1 A computerized device 100 and a HVAC system 10 having a plurality of fan coil units 11-14. Without loss of generality, Figure 3 Room 1 has four fan coil units 11, 12, 13 and 14.

[0056] Reference Figure 1 , a computerized device 100 for controlling an HVAC system 10 comprises a providing unit 110 and a determining unit 120. The providing unit 110 is configured to provide a metamodel M for modeling the distribution of a plurality of physical quantities of the air in the room 1. The metamodel M is based on a reduced-order modeling ROM of a plurality of executed simulations S of the physical quantities of a specific room configuration of the room 1. As described above, in Figure 3 An example of such a room configuration for Room 1 is shown in .

[0057] The multiple physical quantities may include air temperature, air velocity, relative humidity, absolute humidity and / or CO2 content of the air. In particular, the metamodel M models the 3D distribution of the multiple physical quantities of the air in the room 1. For example, according to Figure 3, the plurality of executed simulations S may include a CAE simulation applied to a specific room configuration. The room configuration describes in particular the geometry of the room 1, including the area of ​​the room 1, the height of the room 1, the windows 3, 4 of the room 1 and the door 2 of the room 1, the position of the room 1 in the building including the room 1, the number of people in the room 1, the positions of the people in the room 1, the objects in the room 1 (such as Figure 3 table in room 1) and the position of object 5 in room 1.

[0058] The reduced order modeling error ROM may include machine learning, simulation and / or multiple empirical models. The simulation S may be performed for multiple locations in the room 1. Each of the simulations S may be performed based on a set of boundary conditions, in particular different boundary conditions.

[0059] Figure 1 The determination unit 120 of the computerized device 100 is configured to determine at least one value V of a specific physical quantity among a plurality of physical quantities at a specific location in the room 1 using the provided metamodel M and a plurality of measurement values ​​Q of the specific physical quantity measured by a plurality of physical sensors (not shown). In particular, the determination unit 120 is configured to determine the value V of the specific physical quantity at any location in the room 1.

[0060] in addition, Figure 2 A schematic block diagram of a second embodiment of a computerized device 100 for controlling an HVAC system 10 of a room 1 is shown.

[0061] Figure 2 A second embodiment includes Figure 1 All the features of the first embodiment. In addition, Figure 2 The computerized device 100 comprises a receiving unit 130 and a generating unit 140 .

[0062] The receiving unit 130 is configured to receive a request R defining a desired temperature at a desired location in a room, in particular from a user. The receiving unit 130 sends the received request R to the generating unit 140 .

[0063] As reference Figure 1 As described above, the providing unit 110 provides the metamodel M to the determining unit 120. The providing unit 110 may be a memory storing the metamodel M. Alternatively, the metamodel M may be stored in a cloud storage device, and the providing unit 110 may obtain the metamodel M from the cloud storage device and provide it to the determining unit 120. In addition, the determining unit 120 receives measurement values ​​Q of physical quantities measured by a plurality of physical sensors (not shown) arranged at different locations in the room 1.

[0064] Then, the determination unit 120 determines at least one value V of a specific physical quantity at a specific position in the room 1 using the provided meta model M and the measurement value Q provided by the physical sensor in the room 1 .

[0065] Then, the generating unit 140 may generate a control signal C for controlling the HVAC system 10 based on the at least one value V provided by the providing unit 110 , the measurement value Q provided by the physical sensor, and the request R received by the receiving unit 130 .

[0066] In particular, refer to Figure 3 , the generating unit 140 may send Figure 3 The plurality of fan coil units 11 - 14 in the room 1 provide a control signal C or another control signal derived from the control signal C.

[0067] Figure 4 A sequence of method steps of a first embodiment of a method for controlling an HVAC system 10 of a room 1 is shown. Figure 3 An example of a room 1 including an HVAC system 10 is depicted in FIG.

[0068] Figure 4 The method comprises the following method steps 401 and 402:

[0069] In step 401 , a metamodel M is provided that models the distribution of a plurality of physical quantities of the air in room 1 . Metamodel M is based on a reduced-order modeling ROM of a plurality of performed simulations S of physical quantities of a specific room configuration of room 1 .

[0070] In step 402 , at least one value V of a specific physical quantity among a plurality of physical quantities at a specific position in the room 1 is determined using the provided metamodel M and a plurality of measurement values ​​Q of the specific physical quantity measured by a plurality of physical sensors arranged in the room 1 .

[0071] also, Figure 5 A sequence of method steps of a second embodiment of a method for controlling an HVAC system 10 of a room 1 is shown. Figure 5 The method comprises the following method steps 501-504:

[0072] In step 501 , a 3D distribution of a plurality of physical quantities of the air in room 1 is provided.

[0073] In step 502, the 3D distribution is performed in a reduced order modeling ROM, for example using at least one machine learning algorithm. This process of step 502 converts a huge database into an algebraic equation AE of the desired physical quantity provided in step 503. The algebraic equation AE can be easily deployed to the computerized device 100 (see step 504). The computerized device 100 can be called a virtual sensor because it provides the value V of a specific physical quantity at a specific location in the room 1 without a physical sensor.

[0074] Although the invention has been described in terms of preferred embodiments, it will be apparent to those skilled in the art that modifications are possible in all embodiments.

[0075] Reference numerals:

[0076] 1 Room

[0077] 2 doors

[0078] 3 Windows

[0079] 4 Windows

[0080] 5 Objects

[0081] 10HVAC system

[0082] 11 Fan Coil Unit

[0083] 12 Fan Coil Units

[0084] 13 Fan Coil Unit

[0085] 14 Fan Coil Units

[0086] 100 Computerized equipment

[0087] 110 units provided

[0088] 120 Determine unit

[0089] 130 Receiving Unit

[0090] 140 Generation Unit

[0091] AE Algebraic Equations

[0092] C Control signal

[0093] M Metamodel

[0094] Q Measured value of a physical quantity

[0095] R Request

[0096] ROM Reduced Order Modeling

[0097] S Simulation

[0098] V is the value of the physical quantity.

Claims

1. A computerized device (100) for controlling an HVAC system (10) of a room (1), the computerized device (100) comprising: A unit (110) is provided for providing a metamodel (M) for modeling the distribution of a plurality of physical quantities of the air in the room (1), the metamodel (M) being based on a reduced order modeling (ROM) of a plurality of performed simulations (S) of the physical quantities of a specific room configuration of the room (1), and a determining unit (120) for determining at least one value (V) of a specific physical quantity among a plurality of physical quantities at a specific location in a room (1) without a physical sensor, using a provided meta-model (M) and a plurality of measurement values ​​(Q) of the specific physical quantity measured by a plurality of physical sensors arranged at different locations in the room; a receiving unit (130) for receiving a request (R) defining a desired temperature at a desired location in the room (1), and a generating unit (140) for generating a control signal (C) for controlling the HVAC system (10) based on at least one value (V) of the specific physical quantity determined by the determining unit (120) and the received request (R); The simulations (S) are performed for a plurality of locations in the room (1), wherein each simulation (S) is performed based on a set of boundary conditions.

2. The device according to claim 1, characterized in that: The plurality of physical quantities include air temperature, air velocity, relative humidity, absolute humidity and / or CO2 content of the air.

3. The device according to claim 1 or 2, characterized in that: The meta-model (M) models the 3D distribution of multiple physical quantities of the air in the room (1).

4. The device according to claim 1 or 2, characterized in that: The plurality of performed simulations(S) include a CAE simulation applied to a particular room configuration.

5. The device according to claim 1 or 2, characterized in that: The room configuration describes the geometry of the room (1), in particular the area of ​​the room (1), the height of the room (1), the windows (3, 4) of the room (1) and the door (2) of the room (1), the position of the room (1) in the building, the number of people in the room (1), the positions of the people in the room (1), the objects (5) in the room (1) and / or the positions of the objects (5) in the room (1).

6. The device according to claim 1 or 2, characterized in that: The reduced order modeling (ROM) includes machine learning.

7. The device according to claim 1 or 2, characterized in that: The reduced order modeling (ROM) includes simulation and / or multiple empirical models.

8. The device according to claim 1 or 2, characterized in that: The determination unit (120) is configured to determine a value (V) of a specific physical quantity at any location in the room (1).

9. The device according to claim 1 or 2, characterized in that: The metamodel (M) is constructed based on a plurality of parametric simulations (S) which are approximated as a set of algebraic equations (AE) for a set of desired physical quantities using reduced-order modeling (ROM), in particular using machine learning.

10. The device according to claim 9, characterized in that: The set of algebraic equations (AE) is formed as a system of linear equations, where the column vector of the desired physical quantity is equal to the column vector sum of the products and differences of the matrix describing the measured values ​​of the physical quantity and the column vector of the metamodel coefficients.

11. An HVAC system (10), comprising: The computerized device (100) according to any one of claims 1 to 10, and A plurality of fan coil units (11-14) are provided for conditioning at least one property of the air in a room (1), the fan coil units (11-14) being controlled by a computerized device (100).

12. A computer-implemented method for controlling an HVAC system (10) of a room (1), the method comprising: providing (401) a metamodel (M) for modeling the distribution of a plurality of physical quantities of the air in the room (1), said metamodel (M) being based on a reduced order modeling (ROM) of a plurality of performed simulations (S) of the physical quantities of a specific room configuration of the room (1), and Determine (402) at least one value (V) of a specific physical quantity among a plurality of physical quantities at a specific location in a room (1) without a physical sensor using a provided metamodel (M) and a plurality of measurement values ​​(Q) of the specific physical quantity measured by a plurality of physical sensors arranged at different locations in the room; Receiving a request (R) defining a desired temperature at a desired location in a room (1); generating a control signal (C) for controlling the HVAC system (10) based on at least one value (V) of the specific physical quantity determined by the determination unit (120) and the received request (R); The simulations (S) are performed for a plurality of locations in the room (1), wherein each simulation (S) is performed based on a set of boundary conditions.

13. A computer program product comprising program code for performing the method of claim 12, said program code being operative for controlling an HVAC system when executed on at least one computer.

Images