An intelligent control method based on the Internet of Things and an ecological building energy-saving air-conditioning system

Abstract

This invention discloses an IoT-based intelligent control method and an energy-saving air conditioning system for eco-buildings, relating to the field of air conditioning control technology. The method includes: analyzing the disturbance relationship between air conditioning supply conditions and environmental factors in the eco-building based on historical temperature datasets, and setting the initial air conditioning supply volume for the eco-building; constructing a primary airflow response based on the heat gain effect and the initial air conditioning supply volume using radiative heat gain compensation technology; predicting the flow density of different flow groups in the eco-building over future time periods and calculating the Shapley values ​​for different flow groups, constructing a secondary airflow response based on the Shapley values ​​and the initial air conditioning supply volume; combining the primary and secondary airflow responses to generate the optimal air conditioning supply volume, comparing the optimal air conditioning supply volume with the initial air conditioning supply volume, and adjusting the air conditioning supply mode according to the comparison result. This invention enables more precise air conditioning control, ensuring that comfort requirements are met under different environmental conditions.

Description

Technical Field

[0001] This invention relates to the field of air conditioning control technology, and more specifically, to an intelligent control method based on the Internet of Things and an energy-saving air conditioning system for eco-friendly buildings. Background Technology

[0002] An eco-building refers to a building designed and constructed by integrating ecological building concepts. Its core lies in maximizing the use of natural resources and high-efficiency systems to achieve a balance between energy conservation, emission reduction, environmental protection, and indoor comfort. Eco-building energy-saving air conditioning is a key system in eco-buildings used to regulate the indoor thermal environment. It features low energy consumption, high efficiency, and intelligent control, typically combining technologies such as natural ventilation, ground source heat pumps, air conditioning load prediction, and adaptive airflow regulation to deliver air, cooling, and heating on demand, thereby achieving the goal of maximizing energy savings.

[0003] Current air conditioning control technology primarily relies on stable or relatively gradual changes in solar radiation to predict indoor temperature, thus accurately reflecting temperature variations. However, when solar radiation experiences abrupt changes (such as sudden cloud cover blocking the sun or a sudden weakening of strong sunlight), the existing technology exhibits significant shortcomings, mainly in the following aspects:

[0004] It is not sensitive to mutation response and has difficulty in timely identifying the occurrence and intensity of radiation mutations, resulting in prediction lag;

[0005] The nonlinear response of the indoor thermal environment caused by abrupt changes is quite complex, and existing models lack the ability to describe such high-order disturbances.

[0006] Existing technologies are mostly static or semi-dynamic control mechanisms, lacking the ability to perceive and actively adapt to sudden signals in real time. This makes it difficult to quickly adjust the air conditioning operation strategy to cope with load changes after sudden changes, ultimately affecting indoor environmental comfort and air conditioning system energy efficiency.

[0007] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0008] In response to the problems in related technologies, this invention proposes an intelligent control method based on the Internet of Things and an energy-saving air conditioning system for eco-buildings, so as to overcome the aforementioned technical problems existing in the existing related technologies.

[0009] Therefore, the specific technical solution adopted by the present invention is as follows:

[0010] According to one aspect of the present invention, an intelligent control method based on the Internet of Things is provided, the method comprising:

[0011] Historical temperature data of the eco-building is obtained from the Internet of Things platform. Based on the historical temperature data, the disturbance relationship between air conditioning supply conditions and environmental factors of the eco-building is analyzed, and the initial air conditioning supply volume of the eco-building is set.

[0012] The thermal gain effect of solar radiation on the building envelope of the eco-building was analyzed, and the first-order air volume response of the thermal gain effect and the initial air supply volume was constructed using the radiation thermal gain compensation technology.

[0013] Predict the density of traffic groups in the ecological building in the future and calculate the Shapley value of different traffic groups. Based on the Shapley value, construct a secondary air volume response of traffic groups and initial air supply volume.

[0014] The optimal air conditioning supply volume is generated by combining the primary and secondary air volume responses. The optimal air conditioning supply volume is then compared with the initial air conditioning supply volume, and the air conditioning supply mode is adjusted based on the comparison result.

[0015] Furthermore, the thermal gain effect of solar radiation on the building envelope of the eco-building was analyzed, and the first-order airflow response of the thermal gain effect and the initial air conditioning supply volume was constructed using radiative thermal gain compensation technology, including:

[0016] A finite element model of the building envelope was established using finite element analysis technology. Excessive light radiation ranges were marked in the finite element model, and the time-by-time dynamic penetration process of light radiation through wall and window components was simulated within the excessive light radiation ranges.

[0017] The temperature gradient change of the enclosure structure during dynamic infiltration is analyzed. The temperature gradient change is used as the input of a pre-built Monte Carlo model. The Monte Carlo model generates a photoradiation mutation sequence, and the critical conditions for compensation failure are identified from the photoradiation mutation sequence.

[0018] Based on the critical condition of compensated failure, the thermal gain of the building envelope caused by sudden changes in light radiation is quantified, and the impact intensity of sudden changes in light radiation on the air inside the ecological building is identified by the sparse identification algorithm.

[0019] The first-order air volume response under abrupt change in light radiation and the initial air conditioning air volume is analyzed when they come into contact. The first-order air volume response is then transformed into a first-order matrix using a state-space model.

[0020] Furthermore, the temperature gradient change of the retaining structure during dynamic permeability is analyzed. This temperature gradient change is used as input to a pre-constructed Monte Carlo model. The Monte Carlo model generates a sudden change sequence of light radiation, and the critical conditions for compensation failure are identified from this sequence.

[0021] By incorporating the material properties of the building envelope, the convective heat transfer coefficient between the outer surface and the air, and the heat flux density of the inner surface into a predefined unsteady-state heat conduction equation, a three-dimensional transient heat transfer equation is obtained.

[0022] The temperature gradient change of the building envelope was obtained by solving the three-dimensional transient heat transfer equation using a correlation analysis algorithm.

[0023] A Monte Carlo model was constructed, and the temperature gradient change was input into the Monte Carlo model to identify the statistical characteristics of the abrupt change in light radiation. The statistical characteristics of the abrupt change in light radiation were then used to synthesize a light radiation abrupt change sequence.

[0024] By using batch simulation to statistically analyze failure events and their corresponding failure radiation amplitudes in the abrupt change sequence of light radiation, statistical characteristics corresponding to failure radiation amplitudes within a preset range are selected as critical conditions for compensation failure.

[0025] Furthermore, the sparse identification algorithm was used to identify the impact intensity of sudden changes in light radiation on the air inside the eco-building, including:

[0026] Set the initial number of iterations, error tolerance, and sparsity failure radiation amplitude for the sparse identification algorithm;

[0027] The initial light radiation in contact with the building envelope is extracted from the IoT platform, and the transfer matrix of the thermal gain of the building envelope is calculated based on the initial light radiation. The trend of thermal gain change within each time step is analyzed based on the transfer matrix.

[0028] The inflection point of the thermal gain change trend is selected as the abnormal mutation point of light radiation, and a new transfer matrix is ​​constructed based on the transfer matrix and the abnormal mutation point.

[0029] The impact intensity of sudden changes in light radiation on the air inside the ecological building is calculated iteratively in the new transfer matrix. The impact intensity generated in each iteration is compared with the error tolerance, and the convergence condition is determined based on the comparison results.

[0030] If the convergence condition is met, it means that the sparse identification algorithm has obtained a stable solution, the iteration stops and the impact intensity and its corresponding air environment parameters are output. If the convergence condition is not met, the iteration count is updated and the new iterative calculation process is repeated.

[0031] Furthermore, the impact intensity of abrupt changes in light radiation on the air inside the ecological building is iteratively calculated in the new transfer matrix, including:

[0032] A multilayer feedforward neural network is established using a local recurrent neural network, and feedback neurons are added to the multilayer feedforward neural network. At the same time, the input and output terminals of the multilayer feedforward neural network are updated.

[0033] The impact intensity at future moments is recursively calculated based on the calculation results of the previous moment in the multilayer feedforward neural network. The new transfer matrix is ​​used as the state update mechanism in each iteration so that the impact of sudden changes in light radiation on the air inside the ecological building can be transmitted through the multilayer feedforward neural network.

[0034] The weights of the new transfer matrix are adjusted in real time during the training process by using the gradient descent algorithm to train the multilayer feedforward neural network.

[0035] In the trained multilayer feedforward neural network, the weights based on the new transfer matrix guide the output of the impact intensity of the sudden change in light radiation on the air inside the ecological building at each time step.

[0036] Furthermore, the optimal air conditioning supply air volume is generated by combining the primary and secondary air volume responses, and then compared with the initial air conditioning supply air volume. Based on the comparison result, the air conditioning supply mode is adjusted as follows:

[0037] The contributions of the primary and secondary air volume responses to the air quality inside the eco-building were calculated separately, and a multi-objective optimization model was constructed based on the contributions.

[0038] The order of superiority of primary and secondary air volume response is evaluated based on the superiority-inferiority distance method. The comfort deviation, energy consumption, and response time of the air conditioning air supply mode are used as evaluation indicators. The optimal air supply volume under each evaluation indicator is calculated according to the order of superiority and inferiority using a multi-objective optimization model.

[0039] The optimal air supply volume is compared with the initial air supply volume, and the air supply mode of the air conditioner is adjusted based on the comparison result. The air supply mode command is converted into a device control signal and sent to the building control system through the command transmission protocol to realize the adjustment of the air supply mode of the air conditioner.

[0040] Furthermore, the ranking of the first-order and second-order airflow responses based on the superior-inferior solution distance method includes:

[0041] Set up a multi-attribute decision matrix, standardize the multi-attribute decision matrix to obtain a standard matrix, and then weight the standard matrix to obtain a weighted matrix.

[0042] The primary and secondary air volumes are respectively introduced into the weighted matrix as the positive and negative ideal solutions, and the distances from the predefined air conditioning supply air volume configuration scheme to the positive and negative ideal solutions are calculated respectively.

[0043] The calculated distances are sorted, and the order of priority of primary and secondary air volume responses is determined based on the sorting order.

[0044] Furthermore, comparing the optimal air conditioning air volume with the initial air conditioning air volume, and adjusting the air conditioning air supply mode based on the comparison results includes:

[0045] If the optimal air supply volume is greater than the initial air supply volume of the air conditioner, then the air supply intensity of the air conditioner is increased to increase the air supply volume of the air conditioner.

[0046] If the optimal air supply volume is less than the initial air supply volume of the air conditioner, then reduce the air supply intensity of the air conditioner to reduce the air supply volume of the air conditioner.

[0047] If the optimal air supply volume is equal to the initial air supply volume, then the system will operate stably according to the initial air supply volume.

[0048] Furthermore, the primary and secondary air volumes are respectively incorporated into the weighted matrix as the positive and negative ideal solutions. The distances from the predefined air conditioning supply air volume configuration scheme to the positive and negative ideal solutions are calculated, including:

[0049] The air conditioning air volume configuration scheme is normalized according to the target parameters to obtain a weighted matrix. Based on the primary air volume and the secondary air volume, the positive ideal solution and the negative ideal solution in the weighted matrix are defined.

[0050] Calculate the optimal and worst values ​​for each objective parameter in the weighted matrix;

[0051] Based on the optimal value of each objective parameter, calculate the Euclidean distance from the air conditioning air volume configuration scheme to the positive ideal solution;

[0052] Based on the worst value of each objective parameter, calculate the Euclidean distance from the air conditioning air volume configuration scheme to the negative ideal solution.

[0053] According to another aspect of the present invention, an eco-friendly building energy-saving air conditioning system is also provided, the system comprising:

[0054] The initial air volume setting module is used to obtain historical temperature data of the eco-building from the Internet of Things platform, analyze the disturbance relationship between air conditioning supply conditions and environmental factors of the eco-building based on the historical temperature data, and set the initial air conditioning supply volume of the eco-building.

[0055] The thermal effect analysis module is used to analyze the thermal gain effect of solar radiation on the building envelope of the eco-building, and to construct the first-level air volume response of thermal gain effect and initial air conditioning supply volume using radiation thermal gain compensation technology.

[0056] The traffic group analysis module is used to predict the traffic group density of the ecological building in the future time period and calculate the Shapley value of different traffic groups. Based on the Shapley value, a secondary air volume response of the traffic group and the initial air conditioning supply volume is constructed.

[0057] The air supply mode control module is used to generate the optimal air supply volume by combining the primary air volume response and the secondary air volume response, and compare the optimal air supply volume with the initial air supply volume, and adjust the air supply mode of the air conditioner according to the comparison result.

[0058] The beneficial effects of this invention are as follows:

[0059] 1. This invention integrates IoT data, environmental analysis, and intelligent control algorithms to achieve efficient regulation of the air conditioning system in eco-buildings. By analyzing the relationship between air conditioning supply and environmental disturbances through historical temperature datasets, the initial air supply volume can be precisely set to ensure a comfortable indoor environment. Furthermore, through analysis of the thermal gain effect of solar radiation and radiative thermal gain compensation technology, the primary air volume response of the air conditioner can be precisely adjusted to optimize heat load response. Simultaneously, by predicting the flow group density and calculating the Shapley value, the secondary air supply response of the air conditioner is further optimized. Combining the primary and secondary responses generates the optimal air supply volume, which is then compared and adjusted with the initial air supply volume to ensure that the air conditioning system can meet comfort requirements while reducing energy consumption, thereby improving the system's adaptability and energy efficiency.

[0060] 2. This invention, by combining the analysis of the thermal gain effect of light radiation on the building envelope with radiation heat gain compensation technology, can optimize the air volume response of the air conditioner, thereby improving the energy efficiency and comfort of the air conditioning system. At the same time, based on the prediction of flow group density and the calculation of Shapley value, it can accurately identify the impact of different groups on the air conditioning load, thereby dynamically adjusting the air supply volume of the air conditioner, which can improve the adaptive capability of the air conditioning system, reduce energy waste, ensure indoor environmental comfort and optimize energy efficiency.

[0061] 3. This invention generates the optimal air conditioning air volume by combining the primary and secondary air volume responses, which enables more precise air conditioning adjustment. It ensures that comfort requirements are met under different environmental conditions. After comparing the optimal air volume with the initial air volume, the air supply mode is automatically adjusted according to real-time demand to avoid over-operation or insufficient air supply, thereby reducing energy consumption, improving the operating efficiency and response speed of the air conditioning system, and ensuring that the indoor environment is always in the best condition. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a flowchart of an intelligent control method based on the Internet of Things according to an embodiment of the present invention;

[0064] Figure 2 This is a schematic diagram of an eco-friendly building energy-saving air conditioning system according to an embodiment of the present invention.

[0065] In the picture:

[0066] 1. Initial air volume setting module; 2. Thermal effect analysis module; 3. Flow group analysis module; 4. Air supply mode control module. Detailed Implementation

[0067] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention.

[0068] According to embodiments of the present invention, an Internet of Things-based intelligent control method and an eco-friendly building energy-saving air conditioning system are provided.

[0069] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, according to an embodiment of the present invention, an intelligent control method based on the Internet of Things includes:

[0070] S1. Obtain historical temperature data sets of the eco-building from the IoT platform, analyze the disturbance relationship between air conditioning supply conditions and environmental factors of the eco-building based on the historical temperature data sets, and set the initial air conditioning supply volume of the eco-building.

[0071] It should be noted that historical temperature data for the eco-building is obtained from the IoT platform. Based on this historical temperature data, the relationship between air conditioning supply conditions and environmental factors affecting the eco-building is analyzed, and the initial air conditioning supply volume for the eco-building is set as follows:

[0072] Historical temperature datasets for the eco-building are obtained using an IoT platform or database. These datasets include indoor and outdoor temperatures, air conditioning volume, air supply temperature, humidity, CO2 concentration, light intensity, and equipment operation logs.

[0073] S2. Analyze the thermal gain effect of solar radiation on the building envelope of the eco-building, and use radiation thermal gain compensation technology to construct the first-order air volume response of thermal gain effect and initial air supply volume.

[0074] The analysis of the thermal gain effect of solar radiation on the building envelope of the eco-building, and the construction of a first-order airflow response of the thermal gain effect and the initial air conditioning supply volume using radiative thermal gain compensation technology, includes:

[0075] A finite element model of the building envelope was established using finite element analysis technology. Excessive light radiation ranges were marked in the finite element model, and the time-by-time dynamic penetration process of light radiation through the wall and window components was simulated within these ranges.

[0076] It should be noted that a finite element model of the building envelope was established using finite element analysis technology. Excessive solar radiation regions were marked within the finite element model. Within these regions, the time-by-time dynamic penetration process of solar radiation through the wall and window components was simulated, including:

[0077] A three-dimensional geometric model is constructed in finite element analysis software, defining wall components (thickness, thermal conductivity, density, specific heat capacity) and window components (thickness, thermal conductivity, and transmittance, etc.). Unstructured meshing is performed on the geometry in the three-dimensional model using hexahedral elements, with mesh refinement in high-density regions of solar radiation. Excess radiation zones are defined based on the annual solar trajectory simulation results, and a dynamic radiation heat source is loaded into the three-dimensional geometric model using a time-stepping function, the expression of which is:

[0078] ;

[0079] In the formula, q solar (t) indicates that a dynamic radiative heat source is loaded using a time-stepping function; G solar Indicates solar irradiance; α wall Indicates the wall's absorption rate; τ win Indicates the window's absorption rate; t Represents a timestamp.

[0080] Within the radiation excess range, the total infiltrated heat is calculated by extracting the heat flux density of the walls and windows hourly. The expression is as follows:

[0081] ;

[0082] In the formula, Q total Indicates total osmotic heat; t 1 indicates the start time of the radiation excess zone; t 2 indicates the end time of the radiation excess zone; It represents the heat flux density of the wall surface, that is, the amount of heat passing through the wall per unit time and per unit area; This indicates the heat flux density on the window surface; dA This represents a small area element.

[0083] The temperature gradient change of the retaining structure during dynamic infiltration is analyzed. The temperature gradient change is used as the input of a pre-constructed Monte Carlo model. The Monte Carlo model generates a photoradiation mutation sequence, and the critical conditions for compensation failure are identified from the photoradiation mutation sequence.

[0084] The analysis focuses on the temperature gradient change of the retaining structure during dynamic infiltration. This temperature gradient change is used as input to a pre-built Monte Carlo model. The Monte Carlo model generates a solar radiation mutation sequence, from which critical conditions for compensation failure are identified, including:

[0085] By incorporating the material properties of the building envelope, the convective heat transfer coefficient between the outer surface and the air, and the heat flux density of the inner surface into a predefined unsteady-state heat conduction equation, a three-dimensional transient heat transfer equation is obtained.

[0086] The temperature gradient change of the building envelope was obtained by solving the three-dimensional transient heat transfer equation using a correlation analysis algorithm.

[0087] A Monte Carlo model was constructed, and the temperature gradient change was input into the Monte Carlo model to identify the statistical characteristics of the abrupt changes in light radiation. The statistical characteristics of the abrupt changes in light radiation were then used to synthesize a light radiation abrupt change sequence.

[0088] It should be noted that the construction of the Monte Carlo model to simulate and identify the statistical regularities of abrupt changes in light radiation in the ecological building environment includes: obtaining data on the temperature gradient changes inside and outside the ecological building as input variables for the Monte Carlo model; setting the corresponding probability distribution function based on the fitting relationship between the temperature gradient and the abrupt changes in light radiation; performing random sampling based on the fitting relationship between the temperature gradient and the abrupt changes in light radiation, with each sampling simulating one abrupt change in light radiation event, and integrating the abrupt change events to obtain a set of abrupt change samples, and statistically analyzing the probability density, time interval distribution, and magnitude of change of the abrupt changes from the abrupt change samples.

[0089] By using batch simulation to statistically analyze failure events and their corresponding failure radiation amplitudes in the abrupt change sequence of light radiation, statistical characteristics corresponding to failure radiation amplitudes within a preset range are selected as critical conditions for compensation failure.

[0090] Based on the critical condition of compensation failure, the thermal gain of the building envelope caused by sudden changes in light radiation is quantified, and the impact intensity of sudden changes in light radiation on the air inside the ecological building is identified by the sparse identification algorithm.

[0091] Among them, the impact intensity of sudden changes in light radiation on the air inside the ecological building, identified using sparse identification algorithms, includes:

[0092] Set the initial number of iterations, error tolerance, and sparsity failure radiation amplitude for the sparse identification algorithm;

[0093] The initial light radiation in contact with the building envelope is extracted from the IoT platform, and the transfer matrix of the thermal gain of the building envelope is calculated based on the initial light radiation. The trend of thermal gain change within each time step is analyzed based on the transfer matrix.

[0094] The inflection point of the thermal gain change trend is selected as the abnormal mutation point of light radiation, and a new transfer matrix is ​​constructed based on the transfer matrix and the abnormal mutation point.

[0095] The impact intensity of sudden changes in light radiation on the air inside the ecological building is calculated iteratively in the new transfer matrix. The impact intensity generated in each iteration is compared with the error tolerance, and the convergence condition is determined based on the comparison results.

[0096] The iterative calculation of the impact intensity of sudden changes in light radiation on the air inside the ecological building within the new transfer matrix includes:

[0097] A multilayer feedforward neural network is established using a local recurrent neural network, and feedback neurons are added to the multilayer feedforward neural network. At the same time, the input and output terminals of the multilayer feedforward neural network are updated.

[0098] The impact intensity at future moments is recursively calculated based on the calculation results of the previous moment in the multi-layer feedforward neural network. The new transfer matrix is ​​used as the state update mechanism in each iteration so that the impact of sudden changes in light radiation on the air inside the ecological building is transmitted through the multi-layer feedforward neural network.

[0099] It should be noted that a multilayer feedforward neural network consists of multiple layers of neurons. Each layer takes the output of the previous layer as input and generates its own output through weights and activation functions. Specifically, it includes:

[0100] Step 1: Construct a multi-layer feedforward neural network and dynamically incorporate the impact intensity value output by the network at the previous time step into a recursive structure.

[0101] Step 2: Embed a learnable transfer matrix into the recursive multilayer feedforward neural network. During each forward propagation of the recursive multilayer feedforward neural network, multiply the hidden layer state of the previous time step with the transfer matrix to generate the initial state of the current time step. Then combine it with the current input data to form a dynamically updated network state.

[0102] Step 3: Monitor abrupt events in light radiation (such as sudden increases or decreases in intensity) in real time, and extract the duration of the abrupt change amplitude as a feature through a sliding window. Concatenate the abrupt change features with normal environmental parameters as the input vector of a multilayer feedforward neural network to ensure that the abrupt change signal directly affects the activation mode of the hidden layer.

[0103] The weights of the new transfer matrix are adjusted in real time during the training process by using the gradient descent algorithm to train the multilayer feedforward neural network.

[0104] In the trained multilayer feedforward neural network, the weights based on the new transfer matrix guide the output of the impact intensity of the sudden change in light radiation on the air inside the ecological building at each time step.

[0105] If the convergence condition is met, it means that the sparse identification algorithm has obtained a stable solution, the iteration stops and the impact intensity and its corresponding air environment parameters are output. If the convergence condition is not met, the iteration count is updated and the new iterative calculation process is repeated.

[0106] The first-order air volume response under abrupt change in light radiation and the initial air conditioning air volume is analyzed when they come into contact. The first-order air volume response is then transformed into a first-order matrix using a state-space model.

[0107] S3. Predict the flow density of the ecological building in the future time period and calculate the Shapley value of different flow groups. Based on the Shapley value, construct the secondary air volume response of the flow groups and the initial air supply volume.

[0108] It should be noted that predicting the density of traffic groups in the eco-building over a future period and calculating the Shapeli values ​​for different traffic groups includes:

[0109] Historical pedestrian density data for each area of ​​the eco-building was collected, and the spatial topological relationships of historical pedestrian density were extracted using a building information model. Based on the spatial topological relationships, a spatiotemporal graph convolutional network was constructed, and the feature tensors of a preset historical time period were used as input to the spatiotemporal graph convolutional network. Based on the spatiotemporal graph convolutional network, the pedestrian density of the eco-building in future time periods was predicted. Based on the pedestrian density of the eco-building in future time periods, a feature function was constructed, and the Shapley value was obtained by solving the feature function using Monte Carlo techniques.

[0110] S4. Combine the primary and secondary air volume responses to generate the optimal air conditioning supply volume, compare the optimal air conditioning supply volume with the initial air conditioning supply volume, and adjust the air conditioning supply mode according to the comparison result.

[0111] The optimal air conditioning supply air volume is generated by combining the primary and secondary air volume responses. This optimal air conditioning supply air volume is then compared with the initial air conditioning supply air volume. Based on the comparison result, the air conditioning supply mode is adjusted as follows:

[0112] The contributions of the primary and secondary air volume responses to the air quality inside the eco-building were calculated separately, and a multi-objective optimization model was constructed based on the contributions.

[0113] It should be noted that the multi-objective optimization model includes: constructing evaluation functions, for example, representing the temperature optimization objective function as the contribution of air conditioning air volume to temperature control, and the humidity control objective function as the air conditioning response's ability to control humidity changes; using pre-collected environmental factors of the ecological building as input variables of the multi-objective optimization model, calculating the impact of primary and secondary air volume responses on these environmental factors; and using a genetic algorithm to solve the multi-objective optimization problem, finding the balance point between multiple objectives through several iterations to obtain the optimal air volume adjustment scheme.

[0114] The order of superiority of primary and secondary air volume response is evaluated based on the superiority-inferiority distance method. The comfort deviation, energy consumption, and response time of the air conditioning air supply mode are used as evaluation indicators. The optimal air supply volume of each evaluation indicator is calculated according to the order of superiority and inferiority using a multi-objective optimization model.

[0115] The ranking of the primary and secondary airflow responses based on the superiority-inferiority distance method includes:

[0116] Set up a multi-attribute decision matrix, standardize the multi-attribute decision matrix to obtain a standard matrix, and then weight the standard matrix to obtain a weighted matrix.

[0117] The primary and secondary air volumes are respectively introduced into the weighted matrix as the positive and negative ideal solutions, and the distances from the predefined air conditioning supply air volume configuration scheme to the positive and negative ideal solutions are calculated respectively.

[0118] It should be noted that the primary and secondary air volumes are respectively introduced into the weighted matrix as the positive and negative ideal solutions. The distances from the predefined air conditioning supply air volume configuration scheme to the positive and negative ideal solutions are calculated as follows:

[0119] Different air conditioning air volume configuration schemes are normalized according to target parameters (such as temperature, humidity, energy consumption, etc.) to obtain a weighted matrix; the positive ideal solution and the negative ideal solution are defined in the weighted matrix; the distance from each air conditioning air volume configuration scheme to the positive ideal solution and the negative ideal solution is calculated using Euclidean distance; based on the distance from each air conditioning air volume configuration scheme to the positive ideal solution and the negative ideal solution, the relative distance of each air volume configuration scheme is calculated, and the scheme with the shortest distance to the positive ideal solution and the farthest distance to the negative ideal solution is selected as the optimal solution.

[0120] The calculated distances are sorted, and the order of priority of primary and secondary air volume responses is determined based on the sorting order.

[0121] The optimal air supply volume is compared with the initial air supply volume, and the air supply mode of the air conditioner is adjusted based on the comparison result. The air supply mode command is converted into a device control signal and sent to the building control system through the command transmission protocol to realize the adjustment of the air supply mode of the air conditioner.

[0122] The process of comparing the optimal air conditioning air volume with the initial air conditioning air volume and adjusting the air conditioning air supply mode based on the comparison results includes:

[0123] If the optimal air supply volume is greater than the initial air supply volume of the air conditioner, then the air supply intensity of the air conditioner is increased to increase the air supply volume of the air conditioner.

[0124] If the optimal air supply volume is less than the initial air supply volume of the air conditioner, then reduce the air supply intensity of the air conditioner to reduce the air supply volume of the air conditioner.

[0125] If the optimal air supply volume is equal to the initial air supply volume, then the system will operate stably according to the initial air supply volume.

[0126] According to another embodiment of the invention, such as Figure 2 As shown, an eco-friendly building energy-saving air conditioning system is also provided, the system comprising:

[0127] The initial air volume setting module 1 is used to obtain the historical temperature dataset of the eco-building from the Internet of Things platform, analyze the disturbance relationship between the air conditioning supply conditions and the environmental factors of the eco-building based on the historical temperature dataset, and set the initial air conditioning supply volume of the eco-building.

[0128] The thermal effect analysis module 2 is used to analyze the thermal gain effect of solar radiation on the building envelope of the eco-building, and to construct the first-level air volume response of thermal gain effect and initial air supply volume using radiation thermal gain compensation technology.

[0129] The traffic group analysis module 3 is used to predict the traffic group density in the future time period of the ecological building and calculate the Shapley value of different traffic groups. Based on the Shapley value, a secondary air volume response of traffic groups and initial air supply volume is constructed.

[0130] The air supply mode control module 4 is used to generate the optimal air supply volume by combining the primary air volume response and the secondary air volume response, and compare the optimal air supply volume with the initial air supply volume, and adjust the air supply mode of the air conditioner according to the comparison result.

[0131] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent control method based on the Internet of Things, characterized in that, The method includes: Historical temperature data of the eco-building is obtained from the Internet of Things platform. Based on the historical temperature data, the disturbance relationship between air conditioning supply conditions and environmental factors of the eco-building is analyzed, and the initial air conditioning supply volume of the eco-building is set. The thermal gain effect of solar radiation on the building envelope of the eco-building was analyzed, and the first-order air volume response of the thermal gain effect and the initial air supply volume was constructed using the radiation thermal gain compensation technology. Predict the density of traffic groups in the ecological building in the future and calculate the Shapley value of different traffic groups. Based on the Shapley value, construct a secondary air volume response of traffic groups and initial air supply volume. The optimal air conditioning supply volume is generated by combining the primary and secondary air volume responses, and the optimal air conditioning supply volume is compared with the initial air conditioning supply volume. The air conditioning supply mode is adjusted according to the comparison result. The analysis of the thermal gain effect of solar radiation on the building envelope of the eco-building, and the construction of a first-order airflow response of the thermal gain effect and the initial air conditioning supply volume using radiation thermal gain compensation technology, includes: A finite element model of the building envelope was established using finite element analysis technology. Excessive light radiation ranges were marked in the finite element model, and the time-by-time dynamic penetration process of light radiation through wall and window components was simulated within the excessive light radiation ranges. The temperature gradient change of the enclosure structure during dynamic infiltration is analyzed. The temperature gradient change is used as the input of a pre-built Monte Carlo model. The Monte Carlo model generates a photoradiation mutation sequence, and the critical conditions for compensation failure are identified from the photoradiation mutation sequence. Based on the critical condition of compensated failure, the thermal gain of the building envelope caused by sudden changes in light radiation is quantified, and the impact intensity of sudden changes in light radiation on the air inside the ecological building is identified by the sparse identification algorithm. The first-order air volume response under abrupt change in light radiation and the initial air conditioning air volume is analyzed when they come into contact. The first-order air volume response is then transformed into a first-order matrix using a state-space model.

2. The intelligent control method based on the Internet of Things according to claim 1, characterized in that, The analysis of temperature gradient changes in the retaining structure during dynamic permeability involves using these temperature gradient changes as input to a pre-constructed Monte Carlo model. The Monte Carlo model generates a sequence of abrupt changes in solar radiation, and the critical conditions for compensation failure are identified from this sequence. By incorporating the material properties of the building envelope, the convective heat transfer coefficient between the outer surface and the air, and the heat flux density of the inner surface into a predefined unsteady-state heat conduction equation, a three-dimensional transient heat transfer equation is obtained. The temperature gradient change of the building envelope was obtained by solving the three-dimensional transient heat transfer equation using a correlation analysis algorithm. A Monte Carlo model was constructed, and the temperature gradient change was input into the Monte Carlo model to identify the statistical characteristics of the abrupt change in light radiation. The statistical characteristics of the abrupt change in light radiation were then used to synthesize a light radiation abrupt change sequence. By using batch simulation to statistically analyze failure events and their corresponding failure radiation amplitudes in the abrupt change sequence of light radiation, statistical characteristics corresponding to failure radiation amplitudes within a preset range are selected as critical conditions for compensation failure.

3. The intelligent control method based on the Internet of Things according to claim 2, characterized in that, The method of using sparse identification algorithms to identify the impact intensity of sudden changes in light radiation on the air inside the ecological building includes: Set the initial number of iterations, error tolerance, and sparsity failure radiation amplitude for the sparse identification algorithm; The initial light radiation in contact with the building envelope is extracted from the IoT platform, and the transfer matrix of the thermal gain of the building envelope is calculated based on the initial light radiation. The trend of thermal gain change within each time step is analyzed based on the transfer matrix. The inflection point of the thermal gain change trend is selected as the abnormal mutation point of light radiation, and a new transfer matrix is ​​constructed based on the transfer matrix and the abnormal mutation point. The impact intensity of sudden changes in light radiation on the air inside the ecological building is calculated iteratively in the new transfer matrix. The impact intensity generated in each iteration is compared with the error tolerance, and the convergence condition is determined based on the comparison results. If the convergence condition is met, it means that the sparse identification algorithm has obtained a stable solution, the iteration stops and the impact intensity and its corresponding air environment parameters are output. If the convergence condition is not met, the iteration count is updated and the new iterative calculation process is repeated.

4. The intelligent control method based on the Internet of Things according to claim 3, characterized in that, The iterative calculation of the impact intensity of sudden changes in light radiation on the air inside the ecological building in the new transfer matrix includes: A multilayer feedforward neural network is established using a local recurrent neural network, and feedback neurons are added to the multilayer feedforward neural network. At the same time, the input and output terminals of the multilayer feedforward neural network are updated. The impact intensity at future moments is recursively calculated based on the calculation results of the previous moment in the multilayer feedforward neural network. The new transfer matrix is ​​used as the state update mechanism in each iteration so that the impact of sudden changes in light radiation on the air inside the ecological building can be transmitted through the multilayer feedforward neural network. The weights of the new transfer matrix are adjusted in real time during the training process by using the gradient descent algorithm to train the multilayer feedforward neural network. In the trained multilayer feedforward neural network, the weights based on the new transfer matrix guide the output of the impact intensity of the sudden change in light radiation on the air inside the ecological building at each time step.

5. The intelligent control method based on the Internet of Things according to claim 4, characterized in that, The process of generating the optimal air conditioning supply volume by combining the primary and secondary air volume responses, comparing the optimal air conditioning supply volume with the initial air conditioning supply volume, and adjusting the air conditioning supply mode based on the comparison result includes: The contributions of the primary and secondary air volume responses to the air quality inside the eco-building were calculated separately, and a multi-objective optimization model was constructed based on the contributions. The order of superiority of primary and secondary air volume response is evaluated based on the superiority-inferiority distance method. The comfort deviation, energy consumption, and response time of the air conditioning air supply mode are used as evaluation indicators. The optimal air supply volume under each evaluation indicator is calculated according to the order of superiority and inferiority using a multi-objective optimization model. The optimal air supply volume is compared with the initial air supply volume, and the air supply mode of the air conditioner is adjusted based on the comparison result. The air supply mode command is converted into a device control signal and sent to the building control system through the command transmission protocol to realize the adjustment of the air supply mode of the air conditioner.

6. The intelligent control method based on the Internet of Things according to claim 5, characterized in that, The ranking of the primary and secondary airflow responses based on the superiority-inferiority distance method includes: Set up a multi-attribute decision matrix, standardize the multi-attribute decision matrix to obtain a standard matrix, and then weight the standard matrix to obtain a weighted matrix. The primary and secondary air volumes are respectively introduced into the weighted matrix as the positive and negative ideal solutions, and the distances from the predefined air conditioning supply air volume configuration scheme to the positive and negative ideal solutions are calculated respectively. The calculated distances are sorted, and the order of priority of primary and secondary air volume responses is determined based on the sorting order.

7. The intelligent control method based on the Internet of Things according to claim 6, characterized in that, The step of comparing the optimal air conditioning air volume with the initial air conditioning air volume and adjusting the air conditioning air supply mode based on the comparison result includes: If the optimal air supply volume is greater than the initial air supply volume of the air conditioner, then the air supply intensity of the air conditioner is increased to increase the air supply volume of the air conditioner. If the optimal air supply volume is less than the initial air supply volume of the air conditioner, then reduce the air supply intensity of the air conditioner to reduce the air supply volume of the air conditioner. If the optimal air supply volume is equal to the initial air supply volume, then the system will operate stably according to the initial air supply volume.

8. The intelligent control method based on the Internet of Things according to claim 7, characterized in that, The step of introducing the primary and secondary air volumes into the weighted matrix as the positive and negative ideal solutions, respectively, and calculating the distances from the predefined air conditioning supply air volume configuration scheme to the positive and negative ideal solutions, respectively, includes: The air conditioning air volume configuration scheme is normalized according to the target parameters to obtain a weighted matrix. Based on the primary air volume and the secondary air volume, the positive ideal solution and the negative ideal solution in the weighted matrix are defined. Calculate the optimal and worst values ​​for each objective parameter in the weighted matrix; Based on the optimal value of each objective parameter, calculate the Euclidean distance from the air conditioning air volume configuration scheme to the positive ideal solution; Based on the worst value of each objective parameter, calculate the Euclidean distance from the air conditioning air volume configuration scheme to the negative ideal solution.

9. An eco-friendly building energy-saving air conditioning system, controlled by the Internet of Things-based intelligent control method as described in any one of claims 1-8, characterized in that, The system includes: The initial air volume setting module is used to obtain historical temperature data of the eco-building from the Internet of Things platform, analyze the disturbance relationship between air conditioning supply conditions and environmental factors of the eco-building based on the historical temperature data, and set the initial air conditioning supply volume of the eco-building. The thermal effect analysis module is used to analyze the thermal gain effect of solar radiation on the building envelope of the eco-building, and to construct the first-level air volume response of thermal gain effect and initial air conditioning supply volume using radiation thermal gain compensation technology. The traffic group analysis module is used to predict the traffic group density of the ecological building in the future time period and calculate the Shapley value of different traffic groups. Based on the Shapley value, a secondary air volume response of the traffic group and the initial air conditioning supply volume is constructed. The air supply mode control module is used to generate the optimal air supply volume by combining the primary air volume response and the secondary air volume response, and compare the optimal air supply volume with the initial air supply volume, and adjust the air supply mode of the air conditioner according to the comparison result.

Images