An intelligent temperature control system based on the Internet of Things and cloud computing

Abstract

An intelligent temperature control system based on the Internet of Things and cloud computing relates to the field of intelligent temperature control technology. A three-dimensional twin model of the interior of a building is constructed, a data acquisition terminal is deployed, and a shading data set and a ventilation data set are obtained. The light and heat influence of the interior of the building is obtained based on the shading data set, and the sensible heat influence and latent heat influence of the interior of the building are obtained based on the ventilation data set. Temperature fluctuation values ​​under different influence values ​​are obtained in the three-dimensional twin model, and a fluctuation evaluation model is constructed. The fluctuation evaluation model is used to obtain first-class fluctuation values ​​and second-class fluctuation values ​​respectively. According to the first-class fluctuation values, a first-class adjustment is performed on the equipment to obtain a first-class temperature control solution. According to the second-class fluctuation values, a second-class adjustment is performed on the equipment to obtain a second-class temperature control solution. The system can ensure the stability of the indoor temperature and effectively reduce the energy consumption of the temperature control equipment, which is conducive to the realization of an intelligent temperature control solution.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent temperature control, and in particular to an intelligent temperature control system based on the Internet of Things and cloud computing. Background Art

[0002] Intelligent temperature control is an advanced technology that integrates the Internet of Things, cloud computing, sensors, and automatic control. It uses sensors distributed at various monitoring points to collect relevant data in real time, and transmits the relevant data to the cloud computing platform through the network for storage, analysis, and processing. Based on the analysis results, the temperature control equipment is intelligently controlled to achieve precise and efficient temperature control.

[0003] Most existing technical solutions only perform intelligent adjustment on temperature control devices, achieving temperature control by pre-lowering or raising their set temperature. This adjustment method is too one-sided, fails to coordinate control of different devices inside the building, and ignores the impact of other devices on indoor temperature. To address the shortcomings of the existing technology, the present invention provides an intelligent temperature control system based on the Internet of Things and cloud computing. Summary of the Invention

[0004] The object of the present invention is to provide an intelligent temperature control system based on the Internet of Things and cloud computing.

[0005] The purpose of the present invention can be achieved through the following technical solutions: an intelligent temperature control system based on the Internet of Things and cloud computing, comprising the following modules:

[0006] The data acquisition module is used to obtain structural and equipment information inside the building and build a corresponding 3D twin model. Different data acquisition terminals are deployed at different devices to obtain corresponding multimodal data sets.

[0007] An impact analysis module is used to divide the multimodal data set into a sunshade data set and a ventilation data set, obtain the light and heat impact of the building based on the sunshade data set, and obtain the sensible heat impact and latent heat impact of the building based on the ventilation data set;

[0008] Fluctuation assessment module, used to obtain temperature fluctuation values ​​under different influencing quantities in the 3D twin model and build the corresponding fluctuation assessment model;

[0009] The temperature control module is used to use the fluctuation assessment model to obtain the current Class I fluctuation value and Class II fluctuation value respectively, perform Class I adjustment on the equipment according to the Class I fluctuation value to obtain a Class I temperature control solution, and perform Class II adjustment on the equipment according to the Class II fluctuation value to obtain a Class II temperature control solution.

[0010] Furthermore, the process of obtaining the structural and equipment information inside the building and constructing the corresponding 3D twin model includes:

[0011] The structural information refers to the parameters of different structures inside the building, including the size, position, and shape of walls, floors, beams, columns, pipes, and windows. The equipment information refers to the parameters of different equipment inside the building, including the size, power, position, efficiency, and status of temperature control equipment, sunshade equipment, and ventilation equipment.

[0012] Use BIM technology to build a three-dimensional physical model of the building's interior based on structural information, upload equipment information to the three-dimensional physical model for synchronization, import the three-dimensional physical model containing equipment information into simulation software, and use simulation software to simulate the temperature changes inside the building to obtain a three-dimensional twin model.

[0013] Furthermore, the process of deploying different data collection terminals at different devices and obtaining corresponding multimodal data sets includes:

[0014] The data acquisition terminal includes a temperature control acquisition unit, a sunshade acquisition unit, and a ventilation acquisition unit, and the multimodal data set includes temperature control data, sunshade data, and ventilation data;

[0015] Set up a temperature control acquisition unit on the temperature control device to obtain temperature control data, including mode, indoor temperature, outdoor temperature, cooling / heating capacity, energy efficiency ratio, and cooling / heating power;

[0016] A shading collection unit is set on the shading device, and shading data including transmittance, shading area, light intensity, and ultraviolet intensity are obtained through the shading collection unit. A ventilation collection unit is set on the ventilation equipment, and ventilation data including ventilation volume, indoor humidity, and outdoor humidity are obtained through the ventilation collection unit.

[0017] Furthermore, the multimodal data set is divided into a shading data set and a ventilation data set. The process of obtaining the light and heat impact of the building interior based on the shading data set includes:

[0018] The temperature control data and ventilation data in the multimodal data set are divided into a ventilation data set, and the sunshade data in the multimodal data set are divided into a sunshade data set;

[0019] The transmittance, shading area, and light intensity in the shading dataset are marked as Z a , Z b , Z c , obtain the light and heat impact Q of the shading equipment on the interior of the building g ;

[0020] Q g =S w Z c ·S h +(1-Z a )Zb ·Z c ;

[0021] Among them, S w is the unshaded area of ​​the window, which is equal to the window area minus the shaded area, S h is the preset solar heat gain coefficient. If there are multiple shading devices, the sum of the solar heat impact of each shading device is taken as the total solar heat impact inside the building.

[0022] Furthermore, the process of obtaining the sensible heat impact and latent heat impact inside the building based on the ventilation dataset includes:

[0023] The ventilation volume, indoor temperature, and outdoor temperature in the ventilation dataset are marked as T f 、T in 、T out , obtain the sensible heat impact Q of the ventilation equipment on the interior of the building a ;

[0024]

[0025] Where ρ is the air density, c p is the specific heat capacity of air, V r is the internal volume of the building, T f / V r Indicates the air exchange rate of ventilation equipment;

[0026] The indoor humidity and outdoor humidity in the ventilation dataset are marked as W in 、W out , obtain the latent heat impact Q of ventilation equipment on the interior of the building b ;

[0027]

[0028] Among them, L v is the latent heat coefficient of vaporization of water. If there are multiple ventilation devices, the sum of the sensible heat influence and the sum of the latent heat influence of each ventilation device are taken as the total sensible heat influence and the total latent heat influence inside the building.

[0029] Furthermore, the process of obtaining temperature fluctuation values ​​under different influencing variables in the three-dimensional twin model and constructing the corresponding fluctuation evaluation model includes:

[0030] Upload each data item in the current multimodal data set to the 3D twin model for synchronization, and keep the parameters of different devices unchanged in the 3D twin model;

[0031] Set the evaluation period to obtain the temperature fluctuation value after one evaluation period under the combined effect of the current total light and heat influence, total sensible heat influence, and total latent heat influence;

[0032] Generate a fluctuation evaluation set based on the total amount of light and heat influence, total amount of sensible heat influence, total amount of latent heat influence and their temperature fluctuation values ​​under different multimodal data sets, and divide them into training set and test set;

[0033] Construct a convolutional neural network, use the total amount of photothermal influence, total amount of sensible heat influence, and total amount of latent heat influence under different multimodal data sets in the training set as the input data of the convolutional neural network, and use the corresponding temperature fluctuation values ​​in the training set as the output data of the convolutional neural network;

[0034] The convolutional neural network is trained to obtain an initial convolutional neural network, and the initial convolutional neural network is verified using a test set, and the initial convolutional neural network with a test error threshold less than or equal to a preset test error threshold is output as a fluctuation assessment model.

[0035] Furthermore, the fluctuation assessment model is used to obtain the current first-class fluctuation value and the second-class fluctuation value, and the process of performing a first-class adjustment on the device according to the first-class fluctuation value to obtain a first-class temperature control solution includes:

[0036] When the sunshade and ventilation equipment inside the building change due to human factors, it is regarded as a type of fluctuation. The total amount of light and heat impact, total amount of sensible heat impact, and total amount of latent heat impact under the current multimodal data set are obtained and input into the fluctuation assessment model to obtain the corresponding type of fluctuation value.

[0037] When the shading equipment and ventilation equipment inside the building remain unchanged, but the outdoor environmental conditions change over time, this is regarded as a second-class fluctuation situation. The current total solar heat impact, total sensible heat impact, and total latent heat impact are input into the fluctuation assessment model to obtain the corresponding second-class fluctuation value.

[0038] When a type of fluctuation value is positive, the set temperature of the temperature control device is lowered; when a type of fluctuation value is negative, the set temperature of the temperature control device is increased; when a type of fluctuation value is 0, the set temperature of the temperature control device is not adjusted. The above adjustment content is regarded as a type of temperature control plan.

[0039] Furthermore, the process of performing a second-class adjustment on the device according to the second-class fluctuation value to obtain a second-class temperature control solution includes:

[0040] When the second type of fluctuation value is positive, the sunshade equipment and ventilation equipment are adjusted separately in the three-dimensional twin model, and the adjustment method of reducing the total amount of solar heat impact, the total amount of sensible heat impact, and the total amount of latent heat impact is synchronized to the actual application scenario;

[0041] When the second type of fluctuation value is negative, the sunshade equipment and ventilation equipment are adjusted separately in the three-dimensional twin model, and the adjustment method of increasing the total amount of solar heat influence, the total amount of sensible heat influence, and the total amount of latent heat influence is synchronized with the actual application scenario;

[0042] When the second-class fluctuation value is 0, the sunshade equipment and ventilation equipment are not adjusted, and the above-mentioned adjustment content is used as the second-class temperature control solution.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] By constructing a three-dimensional twin model of the building's interior, the present invention can simulate temperature changes inside the building under different environmental conditions and equipment influences. By obtaining the light and heat influence of the shading equipment, the thermal impact caused by the shading equipment on the building's interior can be evaluated. By obtaining the sensible heat influence and latent heat influence of the ventilation equipment, the thermal impact caused by the ventilation equipment on the building's interior can be evaluated.

[0045] By keeping the current operation of each device unchanged in the three-dimensional twin model and obtaining the temperature fluctuation values ​​under various influencing quantities, the degree of influence of different devices on the indoor temperature can be effectively obtained. By constructing a fluctuation assessment model to directly obtain the current temperature fluctuation value, and by adopting different temperature control schemes inside the building, it is possible to ensure the stability of the indoor temperature and effectively reduce the energy consumption of the temperature control equipment, which is conducive to the realization of intelligent temperature control schemes. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0047] like Figure 1 As shown in the figure, an intelligent temperature control system based on the Internet of Things and cloud computing includes the following modules:

[0048] The data acquisition module is used to obtain structural and equipment information inside the building and build a corresponding 3D twin model. Different data acquisition terminals are deployed at different devices to obtain corresponding multimodal data sets.

[0049] An impact analysis module is used to divide the multimodal data set into a sunshade data set and a ventilation data set, obtain the light and heat impact of the building based on the sunshade data set, and obtain the sensible heat impact and latent heat impact of the building based on the ventilation data set;

[0050] Fluctuation assessment module, used to obtain temperature fluctuation values ​​under different influencing quantities in the 3D twin model and build the corresponding fluctuation assessment model;

[0051] The temperature control module is used to use the fluctuation assessment model to obtain the current Class I fluctuation value and Class II fluctuation value respectively, perform Class I adjustment on the equipment according to the Class I fluctuation value to obtain a Class I temperature control solution, and perform Class II adjustment on the equipment according to the Class II fluctuation value to obtain a Class II temperature control solution.

[0052] It should be further explained that, in the specific implementation process, the process of obtaining the internal structural information and equipment information of the building and constructing the corresponding 3D twin model includes:

[0053] The structural information refers to the parameters of different structures inside the building, including the size, position, shape and other parameters of walls, floors, beams, columns, pipes, windows and other structures; the equipment information refers to the parameters of different equipment inside the building, including temperature control equipment, sunshade equipment, ventilation equipment, etc.

[0054] The temperature control device is exemplified by an air conditioner, the sunshade device is exemplified by a sunshade curtain, and the ventilation device is exemplified by a ventilator. The parameters are used to describe the performance, specifications, characteristics, and other indicators of the device, including size, power, location, efficiency, status, etc.;

[0055] BIM technology is used to construct a three-dimensional physical model of the building's interior based on the collected structural information, and the collected equipment information is uploaded to the constructed three-dimensional physical model for synchronization. The three-dimensional physical model containing the equipment information is imported into the simulation software, and the simulation software is used to simulate the temperature changes inside the building to obtain the corresponding three-dimensional twin model.

[0056] It should be further explained that, in the specific implementation process, different data acquisition terminals are deployed at different devices, and the process of obtaining corresponding multimodal data sets includes:

[0057] For temperature control equipment, a temperature control acquisition unit is set on the temperature control equipment to obtain corresponding temperature control data, including mode, indoor temperature, outdoor temperature, cooling / heating capacity, energy efficiency ratio, cooling / heating power, etc.;

[0058] For sunshade equipment, a sunshade collection unit is set on the sunshade equipment to obtain corresponding sunshade data, including transmittance, sunshade area, light intensity, ultraviolet intensity, etc.;

[0059] For ventilation equipment, a ventilation collection unit is set on the ventilation equipment to obtain corresponding ventilation data, including ventilation volume, indoor humidity, outdoor humidity, etc.;

[0060] The data acquisition end includes a temperature control acquisition unit, a sunshade acquisition unit, and a ventilation acquisition unit, and the multimodal data set includes various data of temperature control data, sunshade data, and ventilation data.

[0061] It should be further explained that, in the specific implementation process, the multimodal data set is divided into a sun shading data set and a ventilation data set. The process of obtaining the light and heat impact of the building interior based on the sun shading data set includes:

[0062] Classifying each item of temperature control data and ventilation data in the multimodal data set into a ventilation data set, and classifying each item of sunshade data in the multimodal data set into a sunshade data set;

[0063] The transmittance, shading area, and light intensity in the shading dataset are marked as Z a , Z b , Z c , obtain the light and heat impact of the shading equipment on the interior of the building and mark it as Q g ;

[0064] Q g =S w Z c ·S h +(1-Z a )Z b ·Z c ;

[0065] Among them, S w is the unshaded area of ​​the window, which is equal to the window area minus the shaded area, S h is the solar heat gain coefficient of the glass, and its value range is 0.1 to 1.0. The above is a method for obtaining the solar heat impact of a single shading device inside a building. If there are multiple shading devices, the sum of their solar heat impacts is used as the total solar heat impact inside the building.

[0066] It should be further explained that, in the specific implementation process, the process of obtaining the sensible heat impact and latent heat impact inside the building based on the ventilation dataset includes:

[0067] The ventilation volume, indoor temperature, and outdoor temperature in the ventilation dataset are marked as T f 、T in 、T out , obtain the sensible heat impact of the ventilation equipment on the building interior and mark it as Q a ;

[0068]

[0069] Where ρ is the air density, c p is the specific heat capacity of air, V r is the internal volume of the building, T f / V r Indicates the air exchange rate of ventilation equipment;

[0070] The indoor humidity and outdoor humidity in the ventilation dataset are marked as W in 、W out , obtain the latent heat impact of ventilation equipment on the interior of the building and mark it as Q b ;

[0071]

[0072] Among them, L v is the latent heat of vaporization coefficient of water, which is 2.45×10 6 J / kg. The above is the method of obtaining the sensible heat influence and latent heat influence of a single ventilation device inside a building. If there are multiple ventilation devices, the sum of their sensible heat influence and the sum of their latent heat influence are respectively taken as the total sensible heat influence and the total latent heat influence inside the building.

[0073] It should be further explained that, in the specific implementation process, the process of obtaining temperature fluctuation values ​​under different influencing quantities in the 3D twin model and constructing the corresponding fluctuation assessment model includes:

[0074] Upload each data item in the current multimodal data set to the 3D twin model for synchronization, and keep the parameters of different devices unchanged in the 3D twin model;

[0075] Set an evaluation cycle to obtain the temperature fluctuation value after one evaluation cycle under the combined effects of the current total solar heat impact, total sensible heat impact, and total latent heat impact. The temperature fluctuation value refers to the change in indoor temperature after one evaluation cycle under the combined effects of the above.

[0076] According to the total amount of light and heat influence, total amount of sensible heat influence, total amount of latent heat influence and their temperature fluctuation values ​​under different multimodal data sets, a corresponding fluctuation evaluation set is generated, and the fluctuation evaluation set is divided into a training set and a test set;

[0077] Construct a convolutional neural network, use the total amount of photothermal influence, total amount of sensible heat influence, and total amount of latent heat influence under different multimodal data sets in the training set as the input data of the convolutional neural network, and use the corresponding temperature fluctuation values ​​in the training set as the output data of the convolutional neural network;

[0078] The convolutional neural network is trained to obtain an initial convolutional neural network, and the initial convolutional neural network is verified using a test set, and the initial convolutional neural network with a preset test error threshold is output as the corresponding fluctuation assessment model.

[0079] It should be further explained that, in the specific implementation process, the fluctuation assessment model is used to obtain the current Class I fluctuation value and Class II fluctuation value, and the process of performing Class I adjustments on the equipment according to the Class I fluctuation value to obtain a Class I temperature control solution includes:

[0080] When the sunshade and ventilation equipment inside the building change due to human factors, it is analyzed as a type of fluctuation. The total amount of light and heat impact, total amount of sensible heat impact, and total amount of latent heat impact under the current multimodal data set are obtained and input into the fluctuation assessment model to obtain the corresponding temperature fluctuation value, which is recorded as a type of fluctuation value.

[0081] When the shading and ventilation equipment inside the building remain unchanged, while the outdoor environmental conditions change over time, this is analyzed as a second-class fluctuation situation. The total amount of light and heat influence, total amount of sensible heat influence, and total amount of latent heat influence under the current multimodal data set are obtained and input into the fluctuation assessment model to obtain the corresponding temperature fluctuation value, which is recorded as the second-class fluctuation value.

[0082] When the obtained fluctuation value is positive, the set temperature of the temperature control device is lowered; when the obtained fluctuation value is negative, the set temperature of the temperature control device is increased; when the obtained fluctuation value is 0, no adjustment is made to the set temperature of the temperature control device. The above is a type of adjustment method, and its adjustment content is marked as a type of temperature control plan.

[0083] It should be further explained that, in the specific implementation process, the process of performing the second-class adjustment on the equipment according to the second-class fluctuation value to obtain the second-class temperature control solution includes:

[0084] When the second type of fluctuation value obtained is positive, the sunshade equipment and ventilation equipment are adjusted separately in the three-dimensional twin model, and the adjustment method of reducing the total amount of solar heat impact, the total amount of sensible heat impact, and the total amount of latent heat impact is synchronized to the actual application scenario;

[0085] When the second-category fluctuation value obtained is negative, the sunshade equipment and ventilation equipment are adjusted separately in the three-dimensional twin model, and the adjustment method of increasing the total amount of solar heat influence, the total amount of sensible heat influence, and the total amount of latent heat influence is synchronized with the actual application scenario;

[0086] When the obtained second-class fluctuation value is 0, no adjustment is made to the sunshade equipment and the ventilation equipment. The above is the second-class adjustment method, and its adjustment content is marked as the second-class temperature control solution.

[0087] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent temperature control system based on the Internet of Things and cloud computing, characterized in that: Includes the following modules: The data acquisition module is used to obtain structural and equipment information inside the building and build a corresponding 3D twin model. Different data acquisition terminals are deployed at different devices to obtain corresponding multimodal data sets. An impact analysis module is used to divide the multimodal data set into a sunshade data set and a ventilation data set, obtain the light and heat impact of the building based on the sunshade data set, and obtain the sensible heat impact and latent heat impact of the building based on the ventilation data set; Fluctuation assessment module, used to obtain temperature fluctuation values ​​under different influencing quantities in the 3D twin model and build the corresponding fluctuation assessment model; A temperature control module is used to use a fluctuation assessment model to obtain the current first-class fluctuation value and second-class fluctuation value, perform first-class adjustment on the device according to the first-class fluctuation value to obtain a first-class temperature control solution, and perform second-class adjustment on the device according to the second-class fluctuation value to obtain a second-class temperature control solution; The process of obtaining the solar thermal impact quantity based on the shading dataset includes: The temperature control data and ventilation data in the multimodal data set are divided into a ventilation data set, and the sunshade data in the multimodal data set are divided into a sunshade data set; The transmittance, shading area, and light intensity in the shading dataset are marked as Z a 、Z b 、Z c , obtain the light and heat impact Q of the shading equipment on the interior of the building g ; Among them, S w is the unshaded area of ​​the window, which is equal to the window area minus the shaded area, S h is the preset solar heat gain coefficient. If there are multiple shading devices, the sum of the solar heat impact of each shading device is taken as the total solar heat impact inside the building; The process of obtaining the sensible heat influence and latent heat influence from the ventilation data set includes: The ventilation volume, indoor temperature, and outdoor temperature in the ventilation dataset are marked as T f 、T in 、T out , obtain the sensible heat impact Q of the ventilation equipment on the interior of the building a ; in, is the air density, c p is the specific heat capacity of air, V r is the internal volume of the building, T f / V r Indicates the air exchange rate of ventilation equipment; The indoor humidity and outdoor humidity in the ventilation dataset are marked as W in 、W out , obtain the latent heat impact Q of ventilation equipment on the interior of the building b ; Among them, L v is the latent heat coefficient of vaporization of water. If there are multiple ventilation devices, the sum of the sensible heat influence and the sum of the latent heat influence of each ventilation device are taken as the total sensible heat influence and the total latent heat influence inside the building; The process of obtaining the first and second type fluctuation values ​​and performing the first type adjustment on the equipment includes: When the sunshade and ventilation equipment inside the building change due to human factors, it is regarded as a type of fluctuation. The total amount of light and heat impact, total amount of sensible heat impact, and total amount of latent heat impact under the current multimodal data set are obtained and input into the fluctuation assessment model to obtain the corresponding type of fluctuation value. When the shading equipment and ventilation equipment inside the building remain unchanged, but the outdoor environmental conditions change over time, this is regarded as a second-class fluctuation situation. The current total solar heat impact, total sensible heat impact, and total latent heat impact are input into the fluctuation assessment model to obtain the corresponding second-class fluctuation value. When the first type of fluctuation value is a positive value, the set temperature of the temperature control device is lowered; when the first type of fluctuation value is a negative value, the set temperature of the temperature control device is increased; when the first type of fluctuation value is 0, the set temperature of the temperature control device is not adjusted. The above adjustment content is regarded as a first type of temperature control plan; The process for performing a Category II regulation on a device includes: When the second type of fluctuation value is positive, the sunshade equipment and ventilation equipment are adjusted separately in the three-dimensional twin model, and the adjustment method of reducing the total amount of solar heat impact, the total amount of sensible heat impact, and the total amount of latent heat impact is synchronized to the actual application scenario; When the second type of fluctuation value is negative, the sunshade equipment and ventilation equipment are adjusted separately in the three-dimensional twin model, and the adjustment method of increasing the total amount of solar heat influence, the total amount of sensible heat influence, and the total amount of latent heat influence is synchronized with the actual application scenario; When the second-class fluctuation value is 0, the sunshade equipment and ventilation equipment are not adjusted, and the above-mentioned adjustment content is used as the second-class temperature control solution.

2. The intelligent temperature control system based on the Internet of Things and cloud computing according to claim 1 is characterized in that: The process of obtaining structural and device information and building a 3D twin model includes: The structural information refers to the parameters of different structures inside the building, including the size, position, and shape of walls, floors, beams, columns, pipes, and windows. The equipment information refers to the parameters of different equipment inside the building, including the size, power, position, efficiency, and status of temperature control equipment, sunshade equipment, and ventilation equipment. Use BIM technology to build a three-dimensional physical model of the building's interior based on structural information, upload equipment information to the three-dimensional physical model for synchronization, import the three-dimensional physical model containing equipment information into simulation software, and use simulation software to simulate the temperature changes inside the building to obtain a three-dimensional twin model.

3. The intelligent temperature control system based on the Internet of Things and cloud computing according to claim 2 is characterized in that: The process of deploying the data collection terminal and obtaining a multimodal data set includes: The data acquisition terminal includes a temperature control acquisition unit, a sunshade acquisition unit, and a ventilation acquisition unit, and the multimodal data set includes temperature control data, sunshade data, and ventilation data; Set up a temperature control acquisition unit on the temperature control device to obtain temperature control data, including mode, indoor temperature, outdoor temperature, cooling / heating capacity, energy efficiency ratio, and cooling / heating power; A shading collection unit is set on the shading device, and shading data including transmittance, shading area, light intensity, and ultraviolet intensity are obtained through the shading collection unit. A ventilation collection unit is set on the ventilation equipment, and ventilation data including ventilation volume, indoor humidity, and outdoor humidity are obtained through the ventilation collection unit.

4. The intelligent temperature control system based on the Internet of Things and cloud computing according to claim 3 is characterized in that: The process of obtaining temperature fluctuation values ​​and building a fluctuation assessment model includes: Upload each data item in the current multimodal data set to the 3D twin model for synchronization, and keep the parameters of different devices unchanged in the 3D twin model; Set the evaluation period to obtain the temperature fluctuation value after one evaluation period under the combined effect of the current total light and heat influence, total sensible heat influence, and total latent heat influence; Generate a fluctuation evaluation set based on the total amount of light and heat influence, total amount of sensible heat influence, total amount of latent heat influence and their temperature fluctuation values ​​under different multimodal data sets, and divide them into training set and test set; Construct a convolutional neural network, use the total amount of photothermal influence, total amount of sensible heat influence, and total amount of latent heat influence under different multimodal data sets in the training set as the input data of the convolutional neural network, and use the corresponding temperature fluctuation values ​​in the training set as the output data of the convolutional neural network; The convolutional neural network is trained to obtain an initial convolutional neural network, and the initial convolutional neural network is verified using a test set, and the initial convolutional neural network with a test error threshold less than or equal to a preset test error threshold is output as a fluctuation assessment model.

Images