A floor radiation cooling system and anti-condensation control method

Abstract

The present invention discloses a floor radiation cooling system and an anti-condensation control method, which relate to the technical field of radiation air conditioning. The method comprises: real-time collection of indoor temperature and humidity, electric three-way valve opening, water pump flow and fresh air unit parameters; using particle swarm algorithm (PSO) to optimize radial basis function neural network (RBF) weights and construct a PSO-RBF prediction model; inputting indoor air temperature, relative humidity, fresh air speed, fresh air humidity, valve opening and water pump flow into the model, outputting surface temperature and calculating condensation risk value with current dew point temperature, dynamically regulating fresh air speed and humidity to achieve anti-condensation; and adjusting the radiation surface temperature based on the PMV thermal comfort model to maintain thermal comfort. The method uses a dual control mechanism to ensure that the radiation surface is prevented from condensation while using the radiation surface to independently bear the sensible heat load, effectively avoiding mold growth and maintaining a stable indoor thermal environment.

Description

Technical Field

[0001] The invention relates to the technical field of radiation air conditioning, and in particular to a floor radiation cooling system and an anti-condensation control method. Background Art

[0002] At present, with the continuous development of society, global energy consumption is increasing year by year. The energy crisis and climate change caused by over-exploitation of fossil energy are challenging people's living environment. For the sustainable development of human society, reducing energy consumption has become the theme of the current era. The energy consumption of air conditioning systems is an important part of global energy consumption.

[0003] Traditional convection air conditioners use a heat and humidity coupling method to control the indoor environment, which will lead to excessive energy consumption. In view of this, people have proposed an independent temperature and humidity control air conditioning system. In this independent temperature and humidity control air conditioning system, the indoor humidity and carbon dioxide are controlled by the fresh air unit. Since the indoor temperature is controlled by the dry terminal, there is no need to undertake the dehumidification task, so the control task of removing waste heat can be achieved with a higher temperature cold source.

[0004] However, when the radiant surface temperature is lower than the indoor dew point temperature, humid air will condense on the radiant surface. The condensation of moisture can cause mold growth and corrode the surface. Summary of the invention

[0005] In view of the shortcomings of the prior art that when the radiation surface temperature is lower than the indoor dew point temperature, humid air will condense on the radiation surface, and the condensation of water will cause mold growth and corrosion of the surface, the present invention proposes a floor radiation cooling system and an anti-condensation control method, which controls the surface temperature above the indoor dew point temperature by adjusting the valve opening, water pump flow, fresh air humidity and fresh air speed of the fresh air unit, thereby preventing condensation and mold growth on the radiation surface, and the radiation surface independently bears the indoor sensible heat load, and the fresh air unit independently bears the indoor latent heat load, thereby solving the problems existing in the prior art.

[0006] A method for preventing condensation in a floor radiant cooling system, comprising the following steps:

[0007] Collecting indoor environmental parameter data sets and the valve opening of the electric three-way valve in the floor radiant cooling system, the water pump flow rate, and the fresh air speed and fresh air humidity of the fresh air unit; the indoor environmental parameter data sets include indoor air temperature, indoor relative humidity, average radiation temperature, indoor wind speed, metabolic rate, and clothing thermal resistance; and obtaining the current indoor dew point temperature based on the indoor air temperature and indoor relative humidity;

[0008] The particle swarm algorithm (PSO) is used to optimize the weights of the radial basis function neural network (RBF) to obtain the PSO-RBF prediction model; the indoor air temperature, indoor relative humidity, fresh air speed, fresh air humidity, valve opening and water pump flow are input into the PSO-RBF prediction model, and the indoor surface temperature is output; the condensation risk value is calculated according to the indoor surface temperature and the current indoor dew point temperature; the fresh air humidity and fresh air speed of the fresh air unit are controlled by the condensation risk value to achieve independent control of the indoor humidity.

[0009] Predicted Mean Vote (PMV) is one of the indicators for evaluating indoor thermal comfort. It reflects the thermal sensation of the human body in the same environment and is related to indoor air temperature, indoor relative humidity, average radiant temperature, indoor wind speed, metabolic rate and clothing thermal resistance. PMV divides thermal sensation into {-3, 22, -1, 0, 1, 2, 3}, corresponding to {very cold, cold, a little cold, neutral, a little hot, hot, very hot}. PMV is output based on the above 6 variables. If PMV is greater than 1, the valve opening is reduced and the water pump flow is increased; if PMV is less than 1, the valve opening is increased and the water pump flow is reduced to achieve independent control of indoor temperature.

[0010] Further, the current indoor dew point temperature is obtained according to the indoor air temperature and the indoor relative humidity. , expressed as:

[0011] ;

[0012] in, t i is the indoor temperature, h i is the indoor relative humidity, and logx is the intermediate variable in the calculation.

[0013] Furthermore, a particle swarm algorithm (PSO) is used to optimize the weights of the radial basis function neural network (RBF) to obtain a PSO-RBF prediction model; the optimization process specifically includes: taking each candidate solution of PSO as a particle, the current position of each particle in the search space as the particle position, the speed at which the particle moves from the current position to the new position in the solution space as the particle speed, and using the mean square error (MSE) of the indoor environmental parameter data set as the fitness function of PSO; the particles adjust their own speed and position according to their own optimal position and the global optimal position, and recalculate the MSE using the updated particle position and speed. After multiple iterations, the minimum MSE value is obtained, and the optimal weight of RBF is obtained, and RBF is optimized according to the optimal weight.

[0014] Furthermore, the activation function of the hidden layer in the optimized RBF is a radial basis function, and its output layer is a single neuron; wherein the output of the hidden layer is:

[0015] ;

[0016] In the formula, μ k and σ k It is k The center and width of neurons in the hidden layer, k is the number of neurons; Input as a sample column vector;

[0017] The output layer is expressed as:

[0018] ;

[0019] In the formula, is the activation function of the kth hidden layer neuron, w k is the kth connection weight.

[0020] Furthermore, the method of optimizing the weights of the radial basis function neural network (RBF) by using the particle swarm algorithm (PSO) also includes setting the particle population size. M , search space D Wei, i The particle position is represented by X i =( x i1 , x i2 ,..., x in ), i =1,2,..., M , No. i Particle speed V i =( v i1 , v i2 ,..., v in ), individual extreme value P i =( p i1 , p i2 ,..., p in ), global extreme value P g =( p g1 , p g2 ,..., p gn ); then the updating formula of the particle velocity and particle position is:

[0021] ;

[0022] ;

[0023] ;

[0024] in, w is the inertia weight, c 1 and c 2 is the acceleration factor, r 1 and r 2 is a random number between 0 and 1, v max is the particle velocity, t Indicates the moment;

[0025] The fitness function is expressed as:

[0026] ;

[0027] in, N is the total number of samples, m is the output node, is the actual output and the expected value.

[0028] The present invention also provides a floor radiation cooling system, comprising:

[0029] A water mixing module is used to control the flow and temperature of the water supply;

[0030] The radiation terminal module includes a water distributor, a water collector and a floor radiation coil, which is used to bear the indoor sensible heat load; wherein the input end of the water distributor and the output end of the water collector are both connected to the water mixing module; the input end of the floor radiation coil is connected to the output end of the water distributor, and its output end is connected to the input end of the water collector;

[0031] The fresh air unit module comprises a fresh air unit and a fresh air duct and a return air duct connected therewith, and is used to bear the latent heat load of the floor radiation coil.

[0032] The control module includes an embedded single chip microcomputer, a wireless gateway, a host computer software and a temperature and humidity sensor, and is used for anti-condensation control of a floor radiant cooling system.

[0033] Furthermore, the water mixing module includes an electric three-way valve, a circulating water pump and a bypass pipe; the three ports of the electric three-way valve are respectively connected to the cold source, the circulating water pump and the bypass pipe; the circulating water pump is connected between the water distributor and the electric three-way valve, and the bypass pipe is connected to the output end of the water collector.

[0034] Furthermore, the embedded single chip microcomputer is connected to the electric three-way valve, circulating water pump, wireless gateway, fresh air unit, and temperature and humidity sensor; the wireless gateway communicates wirelessly with the host computer software.

[0035] The present invention also proposes a computer device for anti-condensation control of a floor radiant cooling system, comprising: a memory, a processor, and a computer program stored in the memory, wherein the processor implements the steps of the anti-condensation control method of the floor radiant cooling system when executing the computer program.

[0036] The present invention also proposes a readable storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, they are used to execute the steps of the anti-condensation control method of the floor radiant cooling system.

[0037] The present invention provides a method for preventing condensation in a floor radiant cooling system, which has the following beneficial effects:

[0038] The present invention adjusts the valve opening, water pump flow, and air supply of the fresh air unit to, on the one hand, control the surface temperature above the indoor dew point temperature to prevent condensation and mold growth on the radiation surface, and the radiation surface independently bears the indoor sensible heat load; on the other hand, an independent fresh air unit is used to ensure the indoor air quality, bear the indoor latent heat load, remove indoor residual moisture, and at the same time meet the thermal comfort requirements of indoor occupants. The intelligent algorithm is used to solve the existing problem that it is difficult to respond quickly to load changes due to the thermal inertia of the radiation cooling terminal, thereby affecting the thermal comfort experience of occupants. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a structural diagram of a floor radiation cooling system in an embodiment of the present invention;

[0040] Figure 2 This is a structural diagram of RBF prediction of condensation risk in an embodiment of the present invention.

[0041] In the figure: 1-electric three-way valve; 2-circulating water pump; 3-bypass pipe; 4-embedded single-chip microcomputer; 5-wireless gateway; 6-host computer software; 7-temperature and humidity sensor; 8-water distributor; 9-water collector; 10-floor radiation coil; 11-fresh air unit; 12-fresh air duct; 13-return air duct. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0043] The present invention proposes a floor radiant cooling system, such as Figure 1 As shown, the floor radiant cooling system specifically includes: a water mixing module, a control module, a radiation terminal module and a fresh air unit module. The water mixing module includes an electric three-way valve 1, a circulating water pump 2, and a bypass pipe 3, which are used to control the floor radiant cooling system. The three ports of the electric three-way valve are respectively connected to the cold source, the circulating water pump and the bypass pipe; the circulating water pump is connected between the water distributor and the electric three-way valve, and the bypass pipe is connected to the output end of the water collector; the electric three-way valve 1 adjusts the flow rate of the bypass pipe 3 by adjusting the valve opening, thereby controlling the water supply temperature. The circulating water pump 2 is a variable frequency water pump, which provides a circulating force for the system. The control module includes an embedded single-chip microcomputer 4, a host computer software 6, a wireless gateway 5 and a temperature and humidity sensor 7. The embedded single-chip microcomputer 4 is used to collect indoor temperature t i , Indoor relative humidity h i , Calculate the indoor dew point temperature t l And upload to the host computer software 6; the embedded single chip computer 4 is connected to the electric three-way valve 1, the circulating water pump 2, the temperature and humidity sensor 7, the wireless gateway 5, and the fresh air unit 11. The host computer software 6 includes an anti-condensation control strategy. The fresh air unit module includes a fresh air unit 11, a fresh air duct 12 and a return air duct 13, which are used to bear the indoor latent heat load. The radiation terminal module includes a water distributor 8, a water collector 9 and a floor radiation coil 10, which are used to bear the indoor sensible heat load; wherein the input end of the water distributor 8 and the output end of the water collector 9 are both connected to the water mixing module; the input end of the floor radiation coil 10 is connected to the output end of the water distributor 8, and its output end is connected to the input end of the water collector 9.

[0044] The present invention provides a method for preventing condensation in a floor radiant cooling system, comprising the following steps:

[0045] S1, using the monitoring platform with embedded single chip microcomputer 4 as the core, using temperature and humidity sensor 7 to collect indoor temperature t i , indoor relative humidity h i .

[0046] S2. According to the collected indoor temperature t i , indoor relative humidity h i Calculate current dew point temperature, indoor dew point temperature t l It can be calculated as follows:

[0047] (1);

[0048] S3. Obtain the operating parameters of the fresh air unit and upload them to the host computer software. The operating parameters of the fresh air unit include fresh air humidity h f , Fresh air speed v f .

[0049] S4. Use RBF neural network to predict PMV index and surface temperature, then use PSO algorithm to improve the weight of RBF neural network and establish PSO-RBF method prediction. PSO-RBF method prediction includes the following steps:

[0050] S4.1. The training process of RBF neural network can be divided into two modes: supervised learning and unsupervised learning. In the network training process, it is necessary to first determine the weights between the input layer and the hidden layer, and between the hidden layer and the output layer. The determination of the number of hidden layer nodes usually relies on empirical formulas for estimation. The mean square error of the sample is used as the fitness function. In the RBF neural network, the neurons in the input layer are selected based on the relevant factors affecting the risk of condensation, while the output layer contains a single neuron (corresponding to the surface temperature t s ), and through the surface temperature t s Calculating the risk of condensation T CR .

[0051] According to the Technical Specification for Radiant Heating and Cooling (JGJ142-2012), the risk of condensation T CR Can be expressed as surface temperature t s 2℃ higher than the indoor air dew point temperature:

[0052] (2);

[0053] The structure of the RBF network is as follows Figure 2 As shown. The input layer is the first layer, and each variable can be used as an input. As the sample column vector input. The hidden layer is the second layer, and the activation function of the hidden layer of the RBF neural network uses the radial basis function. The output of the hidden layer is:

[0054] (3);

[0055] In the formula, μ k and σ k It is k The center and width of neurons in the hidden layer, k is the number of neurons. The output layer is the third layer, and the output of the output layer is:

[0056] (4);

[0057] In the formula, is the activation function of the kth hidden layer neuron, w k is the kth connection weight.

[0058] According to the above, the RBF network inputs the six variables that affect the condensation risk into nodes and outputs one neuron node in the network structure.

[0059] S4.2. Using Particle Swarm Optimization (PSO) to Optimize the Weights of RBF Neural Network w k , each candidate solution in PSO is called a particle. Each particle has a position and speed in the search space. The particle position represents the network weight. A collection of multiple particles is called a population. The population moves continuously in the search space to find the optimal solution. The current position of each particle in the search space is called the particle position, which represents the direction of particle movement. The speed of the particle from the current position to the new position in the solution space is called the particle speed; set the particle population size M, the search space dimension D, the first i The position of a particle is represented by X i =( x i1 , x i2 ,..., x in ), i =1,2,..., M , No. i Particle speed V i =( v i1 , v i2 ,..., v in ), individual extreme value P i =( p i1 , p i2 ,..., p in ), global extreme value P g =( p g1 , p g2 ,..., p gn). Standard particle velocity and position update formula:

[0060] (5);

[0061] (6);

[0062] (7);

[0063] In the formula, w is the inertia weight, c 1 and c 2 is the acceleration factor, r 1 and r 2 is a random number between 0 and 1, v max is the particle velocity, t Indicates time.

[0064] Finally, the mean square error (MSE) of the sample set is used as the fitness function of the algorithm (the particle adjusts its speed and position according to its own optimal position and the global optimal position, recalculates the MSE after updating, and obtains a smaller MSE value through multiple iterations, which is the optimal solution. Use MSE as the fitness function to judge the quality of the particle):

[0065] (8);

[0066] In the formula N is the total number of samples, m is the output node, The actual output and expected value are updated. The individual and global extreme values ​​of particles are updated, and the particle positions and velocities are updated. The maximum number of iterations and the optimal position are determined. The RBF network is optimized using the particle swarm algorithm. The network is trained to finally obtain the condensation risk prediction model, and the fresh air humidity and fresh air speed of the fresh air unit are controlled to achieve independent control of indoor humidity.

[0067] Predicted Mean Vote (PMV) is one of the indicators for evaluating indoor thermal comfort. It reflects the thermal sensation of human body in the same environment and is related to indoor air temperature, indoor relative humidity, average radiant temperature, indoor wind speed, metabolic rate and clothing thermal resistance. PMV divides thermal sensation into {-3, 22, -1, 0, 1, 2, 3}, corresponding to {very cold, cold, a little cold, neutral, a little hot, hot, very hot}. PMV is output according to the above 6 variables.

[0068] The PMV controls the valve opening and the water pump flow rate to achieve independent control of the indoor temperature. If the PMV is greater than 1, the valve opening is reduced and the water pump flow rate is increased; if the PMV is less than 1, the valve opening is increased and the water pump flow rate is reduced; PMV is calculated as follows:

[0069] (9);

[0070] (10);

[0071] (11);

[0072] (12);

[0073] Where M is metabolic rate, W / m 2 ; W m The mechanical work done by the human body is 0W / m 2 ;h c is the convective heat transfer coefficient between the human body and the environment, and h c =8.3v a 0.6 ;f cl is the area coefficient of clothing; t cl is the outer surface temperature of the garment, ℃; t a is the air temperature around the human body, ℃; Pa is the partial pressure of water vapor in the air around the human body, kPa; v a is the air velocity, m / s; I cl is the thermal resistance of clothing, m 2 ·K / W. is the average radiation temperature, °C. φ is the relative humidity of air, %; Ta is the thermodynamic temperature of air, Ta=t a +273.15, K.

[0074] In terms of independent humidity control, the present invention obtains the surface temperature through PSO-RBF prediction, obtains the condensation risk value according to the surface temperature and the current dew point temperature, and controls the fresh air humidity and fresh air speed of the fresh air unit through the condensation risk value. Specifically, if the condensation risk value is less than 2 degrees Celsius, the fresh air unit is controlled to increase the fresh air speed by one gear every 5 minutes and reduce the fresh air humidity by 5 degrees Celsius. If the condensation risk value is greater than 2 degrees Celsius, the fresh air unit is controlled to reduce the fresh air speed by one gear every 5 minutes and keep the fresh air humidity unchanged. In terms of independent temperature control, if PMV is greater than 1, the valve opening is reduced and the water pump flow is increased every 10 minutes; if PMV is less than 1, the valve opening is increased and the water pump flow is reduced to achieve independent control of indoor temperature. Specifically, if PMV is greater than 1, the valve opening is reduced by 10% every 10 minutes, and the water pump flow is increased by 5%. If PMV is less than 1, the valve opening is increased by 10% every 10 minutes, and the water pump flow is reduced by 5%. The valve opening and water pump flow are controlled by the single-chip microcomputer. The valve opening is determined by the output voltage. For every 1V increase, the valve opening increases by 10%. The single-chip microcomputer outputs PWM, the duty cycle increases by 5%, and the water pump flow increases by 5%.

[0075] The present invention also proposes a computer device for anti-condensation control of a floor radiant cooling system, comprising: a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, the steps of the anti-condensation control method of the floor radiant cooling system are implemented.

[0076] The present invention also provides a readable storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, they are used to execute the steps of the anti-condensation control method of the floor radiant cooling system.

[0077] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for preventing condensation in a floor radiant cooling system, characterized in that: The following steps are involved: Collecting indoor environmental parameter data sets and the valve opening of the electric three-way valve in the floor radiant cooling system, the water pump flow rate, and the fresh air speed and fresh air humidity of the fresh air unit; the indoor environmental parameter data sets include indoor air temperature, indoor relative humidity, average radiation temperature, indoor wind speed, metabolic rate, and clothing thermal resistance; and obtaining the current indoor dew point temperature based on the indoor air temperature and indoor relative humidity; The particle swarm algorithm (PSO) is used to optimize the weights of the radial basis function neural network (RBF) to obtain the PSO-RBF prediction model; the indoor air temperature, indoor relative humidity, fresh air speed, fresh air humidity, valve opening and water pump flow are input into the PSO-RBF prediction model, and the indoor surface temperature is output; the condensation risk value is calculated based on the indoor surface temperature and the current indoor dew point temperature; the fresh air humidity and fresh air speed of the fresh air unit are controlled by the condensation risk value to achieve independent control of the indoor humidity; The thermal comfort evaluation index PMV is output according to the indoor air temperature, indoor relative humidity, average radiant temperature, indoor wind speed, metabolic rate and clothing thermal resistance; if PMV is greater than 1, the valve opening is reduced and the water pump flow is increased; if PMV is less than 1, the valve opening is increased and the water pump flow is reduced to achieve independent control of the indoor temperature.

2. The anti-condensation control method of a floor radiant cooling system according to claim 1, characterized in that: The current indoor dew point temperature is obtained according to the indoor air temperature and the indoor relative humidity , expressed as: ； in, t i is the indoor temperature, h i is the indoor relative humidity.

3. The anti-condensation control method of a floor radiant cooling system according to claim 1, characterized in that: The particle swarm algorithm (PSO) is used to optimize the weights of the radial basis function neural network (RBF) to obtain the PSO-RBF prediction model. The optimization process specifically includes: taking each candidate solution of PSO as a particle, the current position of each particle in the search space as the particle position, the speed at which the particle moves from the current position to the new position in the solution space as the particle speed, and using the mean square error (MSE) of the indoor environmental parameter data set as the fitness function of PSO; the particles adjust their own speed and position according to their own optimal position and the global optimal position, and recalculate the MSE using the updated particle position and speed. After multiple iterations, the minimum MSE value is obtained, and the optimal weight of RBF is obtained, and RBF is optimized according to the optimal weight.

4. The anti-condensation control method of a floor radiant cooling system according to claim 3, characterized in that: The activation function of the hidden layer in the optimized RBF is a radial basis function, and its output layer is a single neuron; wherein the output of the hidden layer is: ； In the formula, μ k and σ k It is k The center and width of neurons in the hidden layer, k is the number of neurons; Input as a sample column vector; The output layer is expressed as: ； In the formula, is the activation function of the kth hidden layer neuron, w k is the kth connection weight.

5. The anti-condensation control method of a floor radiant cooling system according to claim 4, characterized in that: The particle swarm algorithm PSO is used to optimize the weights of the radial basis neural network RBF, and also includes setting the particle population size. M , search space D Wei, i The particle position is represented by X i =( x i1 , x i2 ,..., x in ), i =1,2,..., M , No. i Particle speed V i =( v i1 , v i2 ,..., v in ), individual extreme value P i =( p i1 , p i2 ,..., p in ), global extreme value P g =( p g1 , p g2 ,..., p gn ); then the updating formula of the particle velocity and particle position is: ； ； ； in, w is the inertia weight, c 1 and c 2 is the acceleration factor, r 1 and r 2 is a random number between 0 and 1, v max is the particle velocity, t Indicates the moment; The fitness function is expressed as: ； in, N is the total number of samples, m is the output node, is the actual output and the expected value.

6. A floor radiant cooling system, characterized in that: include: A water mixing module is used to control the flow and temperature of the water supply; The radiation terminal module includes a water distributor, a water collector and a floor radiation coil, which is used to bear the indoor sensible heat load; wherein the input end of the water distributor and the output end of the water collector are both connected to the water mixing module; the input end of the floor radiation coil is connected to the output end of the water distributor, and its output end is connected to the input end of the water collector; A fresh air unit module, including a fresh air unit and a fresh air duct and a return air duct connected thereto, for bearing the latent heat load of the floor radiation coil; The control module includes an embedded single chip microcomputer, a wireless gateway, a host computer software and a temperature and humidity sensor, and is used for anti-condensation control of a floor radiant cooling system.

7. A floor radiant cooling system according to claim 6, characterized in that: The water mixing module includes an electric three-way valve, a circulating water pump and a bypass pipe; the three ports of the electric three-way valve are respectively connected to a cold source, a circulating water pump and a bypass pipe; the circulating water pump is connected between the water distributor and the electric three-way valve, and the bypass pipe is connected to the output end of the water collector.

8. A floor radiant cooling system according to claim 6, characterized in that: The embedded single chip microcomputer is connected with the electric three-way valve, the circulating water pump, the wireless gateway, the fresh air unit, and the temperature and humidity sensor; the wireless gateway communicates wirelessly with the host computer software.

9. A computer device for controlling condensation prevention in a floor radiant cooling system, characterized in that: include: A memory, a processor, and a computer program stored in the memory, wherein when the processor executes the computer program, the steps of the anti-condensation control method for a floor radiant cooling system according to any one of claims 1 to 5 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, they are used to execute the steps of the anti-condensation control method for a floor radiant cooling system according to any one of claims 1 to 5.

Images