A method for controlling an air handling unit, an air handling unit, an air handling system, a computer program and a computer program product

Abstract

The disclosure relates to a method (100) for controlling an air handling unit, AHU. The method (100) comprises continuously: generating (S600) an on / off-command configured to switch a regeneration heater on or off based on a comparison between measured humidity levels and a predetermined range of allowable humidity levels; switching (S800) the heater on or off using the generated on / off-command; and controlling (S900) the heater when switched on based on a difference between temperature measurements relating to the temperature of the regeneration air downstream of the heater and a temperature setpoint of the regeneration air downstream of the heater where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest. The disclosure further relates to an air handling unit, an air handling system, a computer program and a computer program product.

Description

[0001] A method for controlling an air handling unit, an air handling unit, an air handling system, a computer program and a computer program product

[0002] Technical field

[0003] The present disclosure relates to a method for controlling an air handling unit, an air handling unit, an air handling system, a computer program and a computer program product. More specifically, the disclosure relates to a method for controlling an air handling unit, an air handling unit, an air handling system, a computer program and a computer program product as defined in the introductory parts of the independent claims.

[0004] Background art

[0005] Air handling units for dehumidification, such as air handling units comprising a desiccant rotor, have many passive and powered components that operate in tandem to process the air. The complex interplay of the passive and powered components of the air handling unit may lead to inefficient power usage. There is thus a need in the art for air handling units with improved energy efficiency.

[0006] Summary

[0007] It is an object of the present disclosure to mitigate, alleviate or eliminate one or more of the above-identified deficiencies and disadvantages in the prior art and solve at least the above-mentioned problem.

[0008] According to a first aspect there is provided a method for controlling an air handling unit, AHU. The AHU comprises a rotor comprising a desiccant material. The AHU further comprises a process air circuit configured to conduct process air through a first sector of the rotor. The AHU also comprises a regeneration air circuit configured to conduct regeneration air through a second sector of the rotor. The AHU additionally comprises a heater configured to heat the regeneration air upstream of the rotor. The AHU further comprises a control unit configured to control the AHU.

[0009] The method comprises continuously: generating an on / off-command configured to switch the heater on or off based on a comparison between one or more measured humidity levels, each measured humidity level relating to a humidity level of process air downstream of the rotor and / or a humidity level of a room to which dehumidified process air is fed downstream of the rotor, and a predetermined range of allowable humidity levels; switching the heater on or off using the generated on / off-command; and controlling the heater when switched on based on a difference between temperature measurements relating to the temperature of the regeneration air downstream of the heater and a temperature setpoint, wherein the temperature setpoint is a temperature of the regeneration air downstream of the heater where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest.

[0010] By continuously switching the heater on or off, the method operates in a nonequilibrium, which allows energy savings when the heater is switched off.

[0011] The desiccant rotor adsorbs moisture from the process air. In order to allow the rotor to continue to adsorb moisture, the moisture that is already adsorbed must be removed. When the heater is switched on, regeneration air is heated to meet the temperature setpoint. If the temperature of the regeneration air is too low, adsorbed moisture at the desiccant rotor will not be released. Likewise, if the temperature of the regeneration air is too high, adsorbed moisture at the desiccant rotor will be released, but some amount of energy will be wasted in the form of excess heat. Thus, the energy savings are further improved by choosing a temperature setpoint where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest.

[0012] According to some examples, generating the on / off-command is performed using a machine learning, ML, model.

[0013] The use of a machine learning model acts synergistically with the choice of controlling the dehumidification process using a non-equilibrium process. The PID-controllers of the prior art are primarily intended to be used in equilibrium processes where oscillations in the controlled system are gradually removed. A ML-model can capture trends and / or patterns in measurement data that allows the oscillations in humidity levels resulting from the on / off- switching to be used to its maximum capacity while staying within any predetermined constraints placed on the humidity levels by a user, such as the predetermined range of allowable humidity levels.

[0014] According to some examples, generating the on / off command further comprises generating, using the ML-model, a prediction of one or more future humidity levels based on the one or more measured humidity levels and temperature measurements relating to a temperature of the regeneration air downstream of the heater. According to some examples, the method comprises obtaining a time series of the one or more measured humidity levels, the time series of the one or more measured humidity levels comprising a current humidity level. The method further comprises obtaining a time series of temperature measurements relating to the temperature of the regeneration air downstream of the heater, the time series of temperatures the method comprises a measurement of a current temperature of the regeneration air downstream of the heater. In these examples generating the on / off-command also comprises generating, using the ML- model, a / the prediction of one or more future humidity levels based on the obtained time series of measurements of humidity levels and time series of temperature measurements, the one or more future humidity levels the method comprises at least one future humidity level.

[0015] According to some examples, generating the on / off-command based on said comparison further comprises generating an on-command based on the comparison indicating a future humidity level exceeding the highest allowable humidity level in the predetermined range of allowable humidity levels; and generating an off-command on the comparison indicating a future and / or present humidity level falling below the lowest allowable humidity level in the predetermined range of allowable humidity levels.

[0016] The predicted future humidity levels enable direct and / or indirect prediction if a future humidity level will potentially fall outside of the predetermined range of allowable humidity levels. By "direct" we herein mean that a predicted future humidity level can be directly compared to the predetermined range of allowable humidity levels. By "indirect prediction" we herein mean that a trend or pattern of the predicted future humidity levels can indicate, e.g. via extrapolation, that some humidity level even further in the future will potentially fall inside or outside of the predetermined range of allowable humidity levels. The indication does not be explicitly calculated in a separate step, but can be determined by the machine learning model as part of the generation of the on / off-command.

[0017] According to some examples, the method comprises transmitting the one or more humidity levels and temperature measurements to a server; and transmitting the generated on / off-command to the AHU. In these examples generating the on / off-command further comprises generating the on / off-command at the server.

[0018] The computational burden can thereby be transferred to the server. The server can act as a cloud service and integrate real world operational data from multiple AHUs in multiple different environments, and thereby train machine learning models that are capable of handling a more diverse set of scenarios than a machine learning model trained at a local AHU in a specific environment.

[0019] According to some examples, the method further comprises: determining the energy consumption required to remove the predetermined amount of moisture from the process air at a plurality of constant temperature setpoints relating to the temperature of the regeneration air downstream of the heater when the AHU is operating at a steady-state and receiving process air having a humidity level within a predetermined interval; and determining the temperature where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest when operating at steady-state and receiving process air having said humidity level within the predetermined interval based on the determined energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints.

[0020] Thus, by testing different temperature setpoints and determine the energy consumption required to remove the predetermined amount of moisture from the process air, the temperature setpoint that requires the least amount of energy for a given amount can be selected.

[0021] According to some examples, determining the energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints comprises selecting a plurality of temperature setpoints relating to the temperature of the regeneration air downstream of the heater. Determining the energy consumption also comprises: for each of the plurality of selected temperature setpoints, measuring a humidity level of the process air downstream of the rotor for a predetermined duration while heating the regeneration air with the heater using the plurality of selected constant temperature setpoints. Determining the energy consumption additionally comprises determining a time interval within the predetermined duration when the AHU is operating at a steady-state based on the measured humidity levels. Determining the energy consumption further comprises determining the energy consumption required to remove the predetermined amount of moisture from the process air based on the measured humidity levels during the time interval.

[0022] The optimal temperature setpoint can thereby be determined during non-equilibrium operational use of the AHU, which is how the AHU is intended to be used. According to some examples, determining the energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints comprises simulating energy transport through the rotor based on a predetermined process air humidity level and air flow, and a predetermined regeneration air flow and constant temperature setpoint relating to the temperature of the regeneration air downstream of the heater; and determining the energy consumption required to remove the predetermined amount of moisture from the process air based on the simulated energy transport.

[0023] Simulating the energy transport enables a deeper understanding of how different factors, such as PID-parameters, and powered and non-powered components of the AHU interact with each other. The energy transport simulation can thus be used to determine additional important parameters for the ML-model.

[0024] A further advantage is that the energy transport simulation can be compared to real- world data, giving an understanding of where the simulation differs from the real-world usage of the AHU. This comparison between simulation and real-world measurements can be used to calibrate the simulation and allow more accurate future energy transport simulations.

[0025] According to a second aspect there is provided an air handling unit, AHU. The AHU comprises a rotor comprising a desiccant material. The AHU further comprises a process air circuit configured to conduct process air through a first sector of the rotor. The AHU also comprises a regeneration air circuit configured to conduct regeneration air through a second sector of the rotor. The AHU additionally comprises a heater configured to heat the regeneration air upstream of the rotor. The AHU also comprises a control system configured to carry of the method according to any of the first aspect.

[0026] The AHU implements the disclosed method according to the first aspect and consequently has all the corresponding technical effects and advantages.

[0027] According to a third aspect there is provided an air handling system comprising: an air handling unit, AHU, according to the second aspect; and a server. The AHU and the server are communicatively connected to each other. The system is configured to carry out the method according to the first aspect.

[0028] The air handling system implements the disclosed method according to the first aspect and consequently has all the corresponding technical effects and advantages. In particular, the presence of a server enables the ML-model to reside at the server which relieves the computational burden from individual AHUs, while simultaneously enabling aggregation of data from multiple AHUs that can be used to further train the ML-model.

[0029] According to a fourth aspect there is provided a computer program comprising computer program code which, when executed by a processor of the control unit of an AHU according to the second aspect, causes the AHU to perform the method according to the first aspect.

[0030] The computer program implements the disclosed method according to the first aspect and consequently has all the corresponding technical effects and advantages.

[0031] According to a fifth aspect there is provided a computer program product comprising a non-transitory computer-readable storage medium having thereon a computer program comprising program instructions, the computer program being loadable into a processor of the control unit of an AHU according to the second aspect and configured to cause the AHU to perform the method according to the first aspect.

[0032] The computer program product implements the disclosed method according to the first aspect and consequently has all the corresponding technical effects and advantages.

[0033] Effects and features of the second through fifth aspects are to a large extent analogous to those described above in connection with the first aspect. Examples mentioned in relation to the first aspect are largely compatible with the second through fifth aspects.

[0034] The present disclosure will become apparent from the detailed description given below. The detailed description and specific examples disclose preferred examples of the disclosure by way of illustration only. Those skilled in the art understand from guidance in the detailed description that changes and modifications may be made within the scope of the disclosure.

[0035] Hence, it is to be understood that the herein disclosed disclosure is not limited to the particular component parts of the device described or steps of the methods described since such device and method may vary. It is also to be understood that the terminology used herein is for purpose of describing particular examples only, and is not intended to be limiting. It should be noted that, as used in the specification and the appended claim, the articles "a", "an", "the", and "said" are intended to mean that there are one or more of the elements unless the context explicitly dictates otherwise. Thus, for example, reference to "a unit" or "the unit" may include several devices, and the like. Furthermore, the words "comprising", "including", "containing" and similar wordings does not exclude other elements or steps.

[0036] Brief of the

[0037] The above objects, as well as additional objects, features and advantages of the present disclosure, will be more fully appreciated by reference to the following illustrative and non-limiting detailed description of example examples of the present disclosure, when taken in conjunction with the accompanying drawings.

[0038] Figures la-lc illustrate method steps of the disclosed method;

[0039] Figure 2 illustrates schematically an air handling unit according to the present disclosure; and

[0040] Figure 3 illustrates schematically an air handling system according to the present disclosure.

[0041] Detailed

[0042] The present disclosure will now be described with reference to the accompanying drawings, in which preferred example examples of the disclosure are shown. The disclosure may, however, be embodied in other forms and should not be construed as limited to the herein disclosed examples. The disclosed examples are provided to fully convey the scope of the disclosure to the skilled person.

[0043] Figures la-lc illustrate method steps of the disclosed method 100 for controlling an air handling unit, AHU, according to the first aspect of the present disclosure. The AHU comprises a rotor comprising a desiccant material. The AHU further comprises a process air circuit configured to conduct process air through a first sector of the rotor. The AHU also comprises a regeneration air circuit configured to conduct regeneration air through a second sector of the rotor. The AHU additionally comprises a heater configured to heat the regeneration air upstream of the rotor. The AHU further comprises a control unit configured to control the AHU. Traditionally such AHUs are controlled by a PID-controller that matches a humidity level of the process air downstream of the desiccant rotor to a desired humidity setpoint. In such cases, the humidity level is gradually brought to the desired humidity setpoint and the AHU preferably ends up operating in a steady-state equilibrium.

[0044] It has been found through experiments and simulations that it is potentially possible to save a lot of energy by instead operating in a continuous non-equilibrium operational mode by switching the heater, and possibly other powered components associated with regeneration, such as a regeneration air fan that drives the regeneration air stream, on or off. Switching the heater on or off will lead to oscillations in the humidity level of the process air downstream of the desiccant rotor, and examples of how the disclosed method 100 handles such challenges are illustrated further below. In some preferred examples, a machine learning model will be used to generate the on / off-commands.

[0045] A further observation of the present disclosure is that the ability of the desiccant rotor to adsorb moisture from the process air is dependent on the temperature of the regeneration air downstream of the heater. In order to adsorb new moisture, previously adsorbed moisture must be released, which is one of the main functions of the regeneration air stream. If the temperature of the regeneration air downstream of the heater is too low, not enough moisture will be regenerated from the desiccant rotor. On the other hand, if the temperature of the regeneration air downstream of the heater is too high, more energy will be spent than needed to desorb a sufficient amount of moisture from the desiccant rotor. An important synergy between temperature setpoint and the heater being switched on or off can thus be had if a temperature setpoint for the regeneration air downstream of the heater is selected where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest when the heater is switched on.

[0046] Thus, the disclosed method 100 comprises continuously generating S600 an on / off- command configured to switch the heater on or off based on a comparison between one or more measured humidity levels, each measured humidity level relating to a humidity level of process air downstream of the rotor and / or a humidity level of a room to which dehumidified process air is fed downstream of the rotor, and a predetermined range of allowable humidity levels. The method 100 further comprises continuously switching S800 the heater on or off using the generated on / off-command. The method 100 also comprises continuously controlling S900 the heater when switched on based on a difference between temperature measurements relating to the temperature of the regeneration air downstream of the heater and a temperature setpoint, wherein the temperature setpoint is a temperature of the regeneration air downstream of the heater where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest.

[0047] The method thereby enables energy savings when the heater is switched off, and a minimum required energy consumption for moisture removal when the heater is switched on, while keeping the humidity levels within the predetermined range of allowable humidity levels.

[0048] According to some examples, generating S600 the on / off-command is performed using a machine learning, ML, model.

[0049] The use of ML-models, such as reinforcement learning, RL, models allow for capturing complex patterns and trends in the measured humidity levels and is thereby optimally suited for controlling the disclosed non-equilibrium process.

[0050] According to some examples, generating S600 the on / off command further comprises generating S610, using the ML-model, a prediction of one or more future humidity levels based the on one or more measured humidity levels and temperature measurements relating to a temperature of the regeneration air downstream of the heater.

[0051] The predicted future humidity levels enable direct and / or indirect prediction if a future humidity level will potentially fall outside of the predetermined range of allowable humidity levels. By "direct" we herein mean that a predicted future humidity level can be directly compared to the predetermined range of allowable humidity levels. By "indirect prediction" we herein mean that a trend or pattern of the predicted future humidity levels can indicate, e.g. via extrapolation, that some humidity level even further in the future will potentially fall inside or outside of the predetermined range of allowable humidity levels. The indication does not be explicitly calculated in a separate step, but can be determined by the machine learning model as part of the generation of the on / off-command. The one or more future humidity levels can in some examples be part of a state of a reinforcement learning algorithm. By including the one or more future humidity levels in a state, a neural network of the RL- algorithm can learn and store, in neural network parameters, optimal actions, that is optimal times to switch the heater on or off, based on the current state of the RL-algorithm.

[0052] According to some examples, the method comprises obtaining S300 a time series of the one or more measured humidity levels, the time series of the one or more measured humidity levels comprising a current humidity level. The method further comprises obtaining S400 a time series of temperature measurements relating to the temperature of the regeneration air downstream of the heater, the time series of temperatures the method comprises a measurement of a current temperature of the regeneration air downstream of the heater. Generating S500 the on / off-command comprises generating S620, using the ML- model, a / the prediction of one or more future humidity levels based on the obtained time series of measurements of humidity levels and time series of temperature measurements, the one or more future humidity levels the method comprising at least one future humidity level.

[0053] By obtaining a time series of humidity levels enables an improvement in the prediction of future humidity levels and / or when to generate an on- or off-command, which in turn enable greater energy savings. If an RL-algorithm is used by the ML-model, one or more humidity levels of the time series of humidity levels may be used as part of a state of the RL- algorithm. The generation S620 of the prediction of one or more future humidity levels can then be modelled as state transitions by the RL-algorithm. The RL-algorithm can thus be used to predict multiple potential humidity levels, which can be analysed for trends and / or patterns by the ML-model to improve prediction accuracy on the best time to generate an on- or off- command.

[0054] According to some examples, generating S600 the on / off-command based on said comparison further comprises generating S630 an on-command based on the comparison indicating a future humidity level exceeding the highest allowable humidity level in the predetermined range of allowable humidity levels; and generating S640 an off-command on the comparison indicating a future and / or present humidity level falling below the lowest allowable humidity level in the predetermined range of allowable humidity levels.

[0055] This allows the method to ensure that the humidity levels stay within the predetermined range of allowable humidity levels, while simultaneously minimizing a difference between a future humidity level and the highest and / or lowest allowable humidity level, thereby improving energy savings.

[0056] According to some examples, the method comprises transmitting S500 the one or more humidity levels and temperature measurements to a server; and transmitting S700 the generated on / off-command to the AHU; wherein generating S600 the on / off-command comprises generating S650 the on / off-command at the server.

[0057] The computational burden can thereby be transferred to the server. The server can act as a cloud service and integrate real world operational data from multiple AHUs in multiple different environments, and thereby train machine learning models that are capable of handling a more diverse set of scenarios than a machine learning model trained at a local AHU in a specific environment. In other words, by generating the on / off-command at a server, the computational burden of the ML-model can be taken of individual AHUs. The use of a cloudbased server that aggregates data from multiple AHU units to optimize the on / off-command generation centrally allows for global optimization of the multiple AHUs. A cloud-based server that gathers data from multiple AHUs, applies RL algorithms, and generates on / off-commands accordingly provides scalability and coordination across large systems.

[0058] According to some examples, the method comprises determining S100 the energy consumption required to remove the predetermined amount of moisture from the process air at a plurality of constant temperature setpoints relating to the temperature of the regeneration air downstream of the heater when the AHU is operating at a steady-state and receiving process air having a humidity level within a predetermined interval. The method further comprises determining S200 the temperature where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest when operating at steady-state and receiving process air having said humidity level within the predetermined interval based on the determined S100 energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints.

[0059] The temperature setpoint that provides the lowest energy consumption required to remove the predetermined amount of moisture from the process air by comparing the energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints with each other and selecting the temperature setpoint requiring the lowest energy consumption to remove the predetermined amount of moisture from the process air.

[0060] According to some examples, determining S100 the energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints comprises selecting S110 a plurality of temperature setpoints relating to the temperature of the regeneration air downstream of the heater. Determining S100 the energy consumption further comprises, for each of the plurality of selected temperature setpoints, measuring S120 a humidity level of the process air downstream of the rotor for a predetermined duration while heating the regeneration air with the heater using the plurality of selected constant temperature setpoints. Determining S100 the energy consumption also comprises determining S130 a time interval within the predetermined duration when the AHU is operating at a steady-state based on the measured S120 humidity levels. Determining S100 the energy consumption additionally comprises determining S140 the energy consumption required to remove the predetermined amount of moisture from the process air based on the measured S120 humidity levels during the time interval.

[0061] Determining S100 the energy consumption required to remove the predetermined amount of moisture can thereby be performed during a non-equilibrium operation of the AHU wherein the heater is being switched on or off as described herein.

[0062] According to some examples, determining S100 the energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints comprises simulating S150 energy transport through the rotor based on a predetermined process air humidity level and air flow, and a predetermined regeneration air flow and constant temperature setpoint relating to the temperature of the regeneration air downstream of the heater; and determining S160 the energy consumption required to remove the predetermined amount of moisture from the process air based on the simulated S150 energy transport.

[0063] Simulating the energy transport enables a deeper understanding of how different factors, such as PID-parameters, and powered and non-powered components of the AHU interact with each other. The energy transport simulation can thus be used to determine additional important parameters for the ML-model.

[0064] A further advantage is that the energy transport simulation can be compared to real- world data, giving an understanding of where the simulation differs from the real-world usage of the AHU. This comparison between simulation and real-world measurements can be used to calibrate the simulation and allow more accurate future energy transport simulations.

[0065] Figure 2 illustrates schematically an air handling unit, AHU, according a second aspect of to the present disclosure. The AHU 200 comprises a rotor 210 comprising a desiccant material. The AHU 200 further comprises a process air circuit SI configured to conduct process air through a first sector zl of the rotor 210. The AHU 200 also comprises a regeneration air circuit S2 configured to conduct regeneration air through a second sector z2 of the rotor 210. The AHU 200 additionally comprises a heater 220 configured to heat the regeneration air upstream of the rotor 210. The AHU 200 further comprises a control system 230 configured to carry of the method 100 according to the first aspect.

[0066] The air handling unit 200 implements the disclosed method 100 for controlling an air handling unit and has the same technical effects and advantages.

[0067] Figure 3 illustrates schematically an air handling system 3000 according a third aspect of the present disclosure. The air handling system 3000 comprises an air handling unit, AHU, 300 according to the second aspect. The air handling system 3000 also comprises a server 350. The AHU 300 and the server 350 are communicatively connected to each other. The system 3000 is configured to carry out the method according to the first aspect.

[0068] The air handling system 3000 implements the disclosed method 100 for controlling an air handling unit and has the same technical effects and advantages. In particular, the use of an external server 350 allows the system 3000 to place the ML-model at the server, the specifics of which have been discussed in relation to figures la-lc above.

[0069] The present disclosure further relates to a computer program according to a fourth aspect, the computer program comprising computer program code which, when executed by a processor of the control unit of an AHU according to the second aspect, causes the AHU to perform the method according to the first aspect.

[0070] The computer program implements the disclosed method 100 for controlling an air handling unit and has the same technical effects and advantages.

[0071] The present disclosure further relates to a computer program product according to a fifth aspect, the computer program product comprising a non-transitory computer-readable storage medium having thereon a computer program comprising program instructions, the computer program being loadable into a processor of the control unit of an AHU according to the second aspect and configured to cause the AHU to perform the method according the first aspect.

[0072] The computer program product implements the disclosed method 100 for controlling an air handling unit and has the same technical effects and advantages.

[0073] The person skilled in the art realizes that the present disclosure is not limited to the preferred examples described above. The person skilled in the art further realizes that modifications and variations are possible within the scope of the appended claims.

[0074] Additionally, variations to the disclosed examples can be understood and effected by the skilled person in practicing the claimed disclosure, from a study of the drawings, the disclosure, and the appended claims.

Claims

CLAIMS1. A method (100) for controlling an air handling unit, AHU, the AHU comprising: a rotor (210, 310) comprising a desiccant material; a process air circuit (SI) configured to conduct process air through a first sector (zl) of the rotor (210, 310); a regeneration air circuit (S2) configured to conduct regeneration air through a second sector (z2) of the rotor (210, 310); a heater (220, 320) configured to heat the regeneration air upstream of the rotor (210, 310); and a control unit (230, 330) configured to control the AHU, the method (100) comprising continuously:- generating (S600) an on / off-command configured to switch the heater on or off based on a comparison between one or more measured humidity levels, each measured humidity level relating to a humidity level of process air downstream of the rotor and / or a humidity level of a room to which dehumidified process air is fed downstream of the rotor, and a predetermined range of allowable humidity levels; switching (S800) the heater on or off using the generated on / off-command; and controlling (S900) the heater when switched on based on a difference between temperature measurements relating to the temperature of the regeneration air downstream of the heater and a temperature setpoint, wherein the temperature setpoint is a temperature of the temperature of the regeneration air downstream of the heater where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest.

2. The method according to claim 1, wherein generating (S600) the on / off-command is performed using a machine learning, ML, model.

3. The method according to claim 2, wherein generating (S600) the on / off command further comprises:- generating (S610), using the ML-model, a prediction of one or more future humidity levels based on the one or more measured humidity levels and temperaturemeasurements relating to a temperature of the regeneration air downstream of the heater.

4. The method (100) according to claim 2 or 3, further comprising obtaining (S300) a time series of the one or more measured humidity levels, the time series of the one or more measured humidity levels comprising a current humidity level; obtaining (S400) a time series of temperature measurements relating to the temperature of the regeneration air downstream of the heater, the time series of temperatures comprising a measurement of a current temperature of the regeneration air downstream of the heater; and wherein generating (S500) the on / off-command comprises:- generating (S620), using the ML-model, a / the prediction of one or more future humidity levels based on the obtained time series of measurements of humidity levels and time series of temperature measurements, the one or more future humidity levels comprising at least one future humidity level.

5. The method according to any of the preceding claims, wherein generating (S600) the on / off-command based on said comparison further comprises- generating (S630) an on-command based on the comparison indicating a future humidity level exceeding the highest allowable humidity level in the predetermined range of allowable humidity levels; and- generating (S640) an off-command on the comparison indicating a future and / or present humidity level falling below the lowest allowable humidity level in the predetermined range of allowable humidity levels.

6. The method according to any of the preceding claims, further comprising- transmitting (S500) the one or more humidity levels and temperature measurements to a server; and17 transmitting (S700) the generated on / off-command to the AHU; wherein generating(S600) the on / off-command comprises generating (S650) the on / off-command at the server.

7. The method (100) according to claim any of the preceding claims, further comprising: determining (S100) the energy consumption required to remove the predetermined amount of moisture from the process air at a plurality of constant temperature setpoints relating to the temperature of the regeneration air downstream of the heater when the AHU is operating at a steady-state and receiving process air having a humidity level within a predetermined interval; and determining (S200) the temperature where the energy consumption required to remove a predetermined amount of moisture from the process air is lowest when operating at steady-state and receiving process air having said humidity level within the predetermined interval based on the determined (S100) energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints.

8. The method (100) according to claim 7, wherein determining (S100) the energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints comprises selecting (S110) a plurality of temperature setpoints relating to the temperature of the regeneration air downstream of the heater;- for each of the plurality of selected temperature setpoints, measuring (S120) a humidity level of the process air downstream of the rotor for a predetermined duration while heating the regeneration air with the heater using the plurality of selected constant temperature setpoints; determining (S130) a time interval within the predetermined duration when the AHU is operating at a steady-state based on the measured (S120) humidity levels; and18 determining (S140) the energy consumption required to remove the predetermined amount of moisture from the process air based on the measured (S120) humidity levels during the time interval.

9. The method according to any of claim 7 or 8, wherein determining (S100) the energy consumption required to remove the predetermined amount of moisture from the process air at the plurality of constant temperature setpoints comprises simulating (S150) energy transport through the rotor based on a predetermined process air humidity level and air flow, and a predetermined regeneration air flow and constant temperature setpoint relating to the temperature of the regeneration air downstream of the heater; and determining (S160) the energy consumption required to remove the predetermined amount of moisture from the process air based on the simulated (S150) energy transport.

10. An air handling unit, AHU, (200, 300) comprising: a rotor (210, 310) comprising a desiccant material; a process air circuit (SI) configured to conduct process air through a first sector (zl) of the rotor (210, 310); a regeneration air circuit (S2) configured to conduct regeneration air through a second sector (z2) of the rotor (210, 310); a heater (220, 320) configured to heat the regeneration air upstream of the rotor (210, 310); and a control system (230, 330) configured to carry of the method (100) according to any of claims 1-9.

11. An air handling system (3000) comprising: air handling unit, AHU, (300) according to claim 10; anda server (350); wherein the AHU (300) and the server (350) are communicatively connected to each other; and wherein the system (3000) is configured to carry out the method according to any of claims 1-9.

12. A computer program comprising computer program code which, when executed by a processor (232, 332) of the control unit (230, 330) of an AHU (200, 300) according to claim 10, causes the AHU (200, 300) to perform the method according to any of claims 1-9.

13. A computer program product comprising a non-transitory computer-readable storage medium having thereon a computer program comprising program instructions, the computer program being loadable into a processor (232, 332) of the control unit (230, 330) of an AHU (200, 300) according to claim 10 and configured to cause the AHU (200, 300) to perform the method according to any of claims 1-9.

Images