Internet of Things central air conditioner intelligent control system and method based on cloud computing

Abstract

The invention discloses an Internet of Things central air conditioner intelligent control system and method based on cloud computing, relates to the technical field of central air conditioner intelligent control, and realizes accurate dynamic regulation and control of a central air conditioner fresh air system through real-time acquisition and fusion analysis of indoor and outdoor multi-dimensional environment data. Compared with a traditional control mode, the method has the advantages that the fresh air volume can be accurately supplied according to actual requirements such as the personnel density and the indoor pollutant concentration, so that the energy consumption of the system is obviously optimized while the indoor air is always kept at a healthy level; according to the invention, through introduction of analysis of historical data and external information, predictive and prospective control is realized. The system can pre-judge future personnel load change and outdoor air quality trend, layout and adjustment of a control strategy are performed in advance, hysteresis of traditional reactive control is effectively avoided, system operation is more stable and efficient, and stability and comfort of an indoor environment are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for central air conditioning, specifically to an IoT-based intelligent control system and method for central air conditioning based on cloud computing. Background Technology

[0002] Central air conditioning systems are an indispensable infrastructure in modern large-scale buildings. Their main function is to create a comfortable and healthy environment for indoor spaces by regulating the temperature, humidity, cleanliness, and airflow speed. This system typically includes cooling or heating equipment, air handling units, and duct systems. The coordinated operation of the fresh air system and the return air system is crucial for maintaining indoor air quality and controlling energy consumption.

[0003] Existing technologies, such as the invention patent application CN118882171B which discloses a multi-source sensor data analysis method and sensing device for an IoT-connected fresh air system, acquire and determine indoor and outdoor air quality parameters through fresh air sensors. Based on the fresh air system, this information is fused and processed. After edge computing analysis, it is correlated and analyzed through a cloud computing platform, and the system dynamically adjusts accordingly. Machine learning is used to deeply analyze the collected data, and data mining algorithms are used to identify patterns and trends, thereby enabling intelligent control and optimization of the industrial fresh air system. Therefore, it is evident that the operation and control methods of central air conditioning systems in existing technologies are relatively traditional. A common approach is to use a fixed fresh air to return air ratio, for example, setting the fresh air valve to always maintain a certain opening during the system design phase to ensure basic ventilation needs. Another slightly more advanced approach is timer-based control, switching operating modes at different times according to a preset schedule. Some systems are also beginning to use single sensors for linkage, such as triggering the fresh air valve to increase its opening when the indoor carbon dioxide concentration exceeds a certain threshold.

[0004] However, the aforementioned existing technical solutions have significant limitations. A fixed fresh air ratio control method cannot adapt to dynamic changes in the number of people indoors. When there are few people, it leads to unnecessary fresh air intake, resulting in significant energy waste. Conversely, when there are many people, a fixed fresh air volume is often insufficient to dilute pollutants, causing a decline in indoor air quality. While a control method based on a single sensor threshold trigger has some dynamism, its response is lagging and it does not comprehensively consider key external factors such as outdoor air quality. This may introduce outdoor pollutants along with fresh air, failing to achieve optimal overall control. Summary of the Invention

[0005] The purpose of this invention is to provide a cloud computing-based Internet of Things (IoT) intelligent control system and method for central air conditioning, which solves the problems existing in the background technology.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The first aspect of the present invention provides a cloud computing-based Internet of Things central air conditioning intelligent control system, including: an environmental data acquisition module, used to acquire indoor environmental parameters and outdoor environmental parameters, and generate real-time environmental data.

[0007] The environmental data processing module is used to send the real-time environmental data to the cloud computing platform for multi-source data fusion processing to generate an environmental state vector.

[0008] The fresh air ratio generation module is used to generate dynamic fresh air ratio parameters based on the environmental state vector and through a dynamic weight adjustment model.

[0009] The control module converts the dynamic fresh air ratio parameters into control commands and sends them to the central air conditioning controller to adjust the opening of the return air valve and the fresh air valve.

[0010] A second aspect of the present invention provides a method for executing the cloud computing-based Internet of Things central air conditioning intelligent control system described in the present invention, comprising: step one, acquiring indoor environmental parameters and outdoor environmental parameters, and generating real-time environmental data.

[0011] Step 2: Send the real-time environmental data to the cloud computing platform for multi-source data fusion processing to generate an environmental state vector.

[0012] Step 3: Based on the environmental state vector, perform calculations using a dynamic weight adjustment model to generate dynamic fresh air ratio parameters.

[0013] Step 4: Convert the dynamic fresh air ratio parameters into control commands and send them to the central air conditioning controller to adjust the opening of the return air valve and the fresh air valve.

[0014] The beneficial effects of this invention are as follows: (1) This invention achieves precise dynamic control of the central air conditioning fresh air system by real-time collection and cloud-based fusion analysis of multi-dimensional indoor and outdoor environmental data. Compared with traditional control methods, this method can accurately supply fresh air volume according to actual needs such as personnel density and indoor pollutant concentration, effectively avoiding excessive ventilation when there are few people or insufficient ventilation when there are many people, thereby ensuring that the indoor air is always at a healthy level while significantly optimizing the system's energy consumption.

[0015] (2) The control decision of this invention is not based on isolated real-time data, but achieves predictive and forward-looking control by introducing the analysis of historical data and external information. The system can predict future changes in personnel load and outdoor air quality trends, and make advance arrangements and adjustments to control strategies, effectively avoiding the lag of traditional reactive control, making the system run more smoothly and efficiently, and further improving the stability and comfort of the indoor environment.

[0016] (3) This invention constructs a closed-loop feedback system with adaptive learning capabilities. By continuously comparing the control effect with the expected target, the system can automatically identify and quantify decision deviations, and iteratively optimize the internal model parameters accordingly. This self-improvement mechanism enables the system to continuously adapt to the long-term evolution of building characteristics, seasonal changes, and user behavior patterns, ensuring the long-term optimality of the control strategy and achieving a high degree of automation and intelligent management. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art 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.

[0018] Figure 1 This is a schematic diagram of the system structure connection of the present invention.

[0019] Figure 2 This is a schematic diagram of the implementation steps of the method of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Reference Figure 1 As shown, the present invention provides a cloud computing-based Internet of Things (IoT) intelligent control system for central air conditioning, including: an environmental data acquisition module, used to acquire indoor environmental parameters and outdoor environmental parameters, and generate real-time environmental data.

[0022] In a specific embodiment of the present invention, the generation of real-time environmental data includes: monitoring indoor CO2 concentration, indoor temperature, indoor humidity and number of people through an Internet of Things sensor network to obtain indoor environmental parameters.

[0023] Outdoor environmental parameters are obtained by monitoring outdoor CO2 and particulate matter concentrations through an Internet of Things (IoT) sensor network.

[0024] It should be noted that the IoT sensor network consists of multiple indoor sensor nodes and one outdoor sensor unit, interconnected via a wireless communication protocol and communicating with a data gateway. Indoors, within the service area of ​​the central air conditioning system, such as conference rooms and open office areas, sensor nodes are deployed in key locations including CO2 sensors based on non-dispersive infrared principles, thermistor temperature sensors, capacitive humidity sensors, and infrared pyroelectric sensors or image analysis modules for estimating the number of people. These sensor nodes operate continuously, monitoring and acquiring indoor CO2 concentration, indoor temperature, indoor humidity, and the number of people in real time. Simultaneously, an outdoor sensor unit is installed outside the building, integrating a CO2 sensor, a laser scattering PM2.5 sensor, and a temperature sensor to monitor outdoor CO2 concentration, outdoor PM2.5 concentration, and outdoor temperature. All sensor measurements, after preliminary processing and digitization, are timestamped and integrated into a structured dataset to generate real-time environmental data.

[0025] By integrating the indoor environmental parameters and the outdoor environmental parameters, the real-time environmental data is generated. .

[0026] in, This represents the indoor CO2 concentration. This represents the indoor temperature. This represents indoor humidity. Number of representatives. This represents the outdoor CO2 concentration. This represents the outdoor PM2.5 concentration. This represents the outdoor temperature.

[0027] The environmental data processing module is used to send the real-time environmental data to the cloud computing platform for multi-source data fusion processing to generate an environmental state vector.

[0028] In a specific embodiment of the present invention, the content of the generated environmental state vector includes: extracting the number of people and the area of ​​the air conditioning monitoring area from the real-time environmental data, and calculating the personnel density characteristics.

[0029] Outdoor CO2 concentration and outdoor particulate matter concentration are extracted from the real-time environmental data, normalized, and then weighted to generate outdoor air quality characteristics.

[0030] It should be noted that the normalization process aims to eliminate the influence of different dimensions of different pollutants, making them comparable.

[0031] The environmental state vector is generated by combining the personnel density characteristics, the outdoor air quality characteristics, and the indoor CO2 concentration extracted from the real-time environmental data. .

[0032] in, For population density characteristics, Characteristics of outdoor air quality This represents the characteristics of indoor CO2 concentration.

[0033] The fresh air ratio generation module is used to generate dynamic fresh air ratio parameters based on the environmental state vector and through a dynamic weight adjustment model.

[0034] In a specific embodiment of the present invention, the calculation performed by the dynamic weight adjustment model includes: calling the dynamic weight adjustment model to generate the final dynamic fresh air ratio parameter. The core of this model is to dynamically adjust the priority of various control objectives based on the real-time values ​​of different features in the environmental state vector.

[0035] Based on the personnel density characteristics in the environmental state vector, a CO2 control weight is dynamically adjusted to characterize the priority of CO2 control.

[0036] It should be noted that the CO2 control weight adjustment amount, which represents the priority of CO2 control, is obtained by matching the personnel density characteristics with the CO2 control weight adjustment table corresponding to each personnel density characteristic interval stored in the data warehouse through the table lookup method. This adjustment amount is then added to the CO2 control weight benchmark in the dynamic weight adjustment model to obtain the CO2 control weight used to represent the priority of CO2 control. When the personnel density characteristic value is high, it indicates that the indoor personnel are densely populated and the risk of CO2 concentration increase is greater. The weight parameter of indoor CO2 concentration in the decision-making process will be increased accordingly, thereby strengthening the system's control over CO2.

[0037] It should also be noted that the generation of the CO2 control weight adjustment table corresponding to each personnel density characteristic interval is based on historical personnel density data of central air conditioning operation, CO2 concentration change failure cases, a large number of experimental test results such as measured data of CO2 exceedance risk under different densities, and combined with the experience of experts in the field, and the personnel density interval division and corresponding adjustment amount are determined after calibration.

[0038] In another specific embodiment, a mathematical expression for the change of CO2 control weight with personnel density characteristics is determined through prior experiments. The personnel density characteristics are directly substituted into the above mathematical expression to obtain the CO2 control weight adjustment amount used to characterize the CO2 control priority. This adjustment amount is then added to the CO2 control weight benchmark amount in the dynamic weight adjustment model to obtain the CO2 control weight used to characterize the CO2 control priority.

[0039] Based on the outdoor air quality characteristics in the environmental state vector, a fresh air introduction weight is dynamically adjusted to characterize the suitability of introducing fresh air.

[0040] It should be noted that when the outdoor air quality characteristic value indicates that the external air quality is poor, the weighting parameter of the fresh air introduction will be reduced, thereby reducing the negative impact of outdoor pollutants on the indoor environment and avoiding unnecessary energy consumption.

[0041] It should also be noted that the method for determining the fresh air introduction weight corresponding to the outdoor air command characteristics, which characterizes the suitability of introducing fresh air, is similar to the method for determining the CO2 control weight applied to the personnel density characteristics, which characterizes the priority of CO2 control, and will not be elaborated here.

[0042] By combining the adjusted CO2 control weights and the fresh air introduction weights, the indoor CO2 concentration in the environmental state vector is calculated to generate the dynamic fresh air ratio parameter.

[0043] This method represents a paradigm shift from passive response to proactive, intelligent trade-offs in control. By dynamically adjusting weighting parameters, the system no longer rigidly executes single threshold control but instead makes optimal trade-off decisions based on real-time indoor occupant load and outdoor air quality. For example, in situations with high population density but severe outdoor air pollution, the system can intelligently balance the conflicting objectives of reducing indoor CO2 concentration and avoiding the introduction of outdoor pollutants, finding a control point that ensures basic health and comfort for occupants while minimizing the adverse effects of the external environment. This collaborative decision-making capability enables the overall system performance to surpass the simple summation of the effects of individual control components, achieving dual optimization of indoor environmental quality and energy efficiency.

[0044] In a specific embodiment of the present invention, the calculation performed by the dynamic weight adjustment model further includes: acquiring historical environmental data and external weather forecast data.

[0045] It should be noted that the historical environmental data is specifically obtained from the cloud computing platform, and the external weather forecast data is specifically obtained by calling the external weather forecast service through the application programming interface.

[0046] Based on the historical environmental data and external weather forecast data, a future population density trend and a future outdoor air quality trend are generated.

[0047] It should be noted that, based on the periodic patterns inherent in historical environmental data, such as peak meeting times on weekdays or sparse crowds on weekends, the system uses a time series forecasting model to generate future population density trends. Simultaneously, based on external weather forecast data, it directly extracts future outdoor air quality trends.

[0048] It should also be noted that the time series prediction model is widely used in the field of environmental data trend prediction, possessing the ability to stably capture the periodic and trend characteristics of data, and can effectively adapt to the system's need to predict the changing patterns of population density. Time series prediction models such as ARIMA, LSTM neural networks, or grey prediction models are used to generate future population density trends. These models can be trained and their parameters tuned using population density data from a past period to capture daily, weekly, and seasonal patterns. Simultaneously, based on external weather forecast data, future outdoor air quality trends are directly extracted or generated through a lightweight ensemble model. The output of this prediction module will be used for forward-looking parameter adjustments of the dynamic weight adjustment model. Since the core of this invention lies in adjusting dynamic weights using the future population density trend output by this model, rather than improving the time series prediction model itself, its specific algorithm principles, parameter settings, and other details will not be elaborated here.

[0049] Based on the future population density trend and the future outdoor air quality trend, the CO2 control weight and the fresh air introduction weight in the dynamic weight adjustment model are proactively adjusted and updated into the parameter set of the dynamic weight adjustment model.

[0050] In one specific embodiment, feature analysis is performed on future trends in population density and future trends in outdoor air quality to extract key changing features from these two trends. These key changing features include, but are not limited to, the continuous increase or decrease in population density and the evolution of outdoor air quality. Based on the extracted key changing features, a preset weight adjustment rule library is invoked. The weight adjustment rule library contains preset correspondences between trend features and weight adjustment directions and priorities. All correspondences are generated based on the logic of trend feature-risk association-weight adaptation. Specifically, if future population density shows a significant increasing trend, it indicates an increased risk of subsequent increases in indoor CO2 concentration. In this case, the decision priority of CO2 control weight should be increased to enhance the system's control effectiveness against subsequent CO2 concentrations. If future outdoor air quality shows a deteriorating trend, it indicates an increased risk of pollutants being introduced with the subsequent fresh air intake. In this case, the decision priority of fresh air intake weight should be decreased to weaken the adverse effects of outdoor pollutants on the indoor environment.

[0051] The CO2 control weight and fresh air introduction weight, adjusted according to the above rules, will be updated into the parameter set of the dynamic weight adjustment model. This will enable the dynamic weight adjustment model to incorporate forward-looking trend information when generating dynamic fresh air ratio parameters in subsequent calculations, adapting to future environmental changes in advance and realizing a shift from a control mode that passively responds to real-time data to one that proactively addresses future changes.

[0052] By adjusting model parameters, the system can proactively alter its response sensitivity or control preferences to specific environmental changes, upgrading the central air conditioning control system from a reactive system relying solely on real-time data to a proactive system with predictive capabilities. By anticipating potential future environmental changes, such as a surge in personnel density due to an upcoming large conference or impending heavy outdoor pollution weather, the system can intervene in advance. For example, it can gradually increase fresh air volume before the conference begins to lower the indoor CO2 concentration baseline, or perform an efficient indoor air replacement before pollution weather arrives. This predictive control strategy effectively smooths the control curve, avoiding control lag and overshoot caused by sudden environmental changes. This ensures a stable indoor environment while further unlocking energy-saving potential, achieving a higher level of intelligent and refined management.

[0053] In a specific embodiment of the present invention, the dynamic weight adjustment model is calculated in the following manner: The numerical features in the environmental state vector, along with the adjusted CO2 control weights and fresh air intake weights, are converted into fuzzy linguistic variables.

[0054] Among them, the CO2 control weight corresponds to the CO2 control priority fuzzy variable, and the fresh air introduction weight corresponds to the fresh air suitability fuzzy variable.

[0055] Fuzzy inference is performed on the aforementioned fuzzy linguistic variables based on a rule base containing expert rules. During the inference process, the triggering weights of corresponding rules are adjusted according to the membership degree of the CO2 control priority and the suitability of fresh air fuzzy variables. For example, when the membership degree of the CO2 control weight is high, the rule of high population density / high indoor CO2 concentration - significantly increased fresh air ratio is triggered first. When the membership degree of the fresh air introduction weight is low, the triggering priority of the rule of poor outdoor air quality - reduced fresh air ratio is reduced.

[0056] The fuzzy inference output after weight adjustment is defuzzified. For example, when using the centroid method, the midpoint of the fuzzy set interval is taken as the precise value to generate the dynamic fresh air ratio parameter.

[0057] In a specific embodiment of the present invention, the indoor environmental parameters further include the indoor volatile organic compound concentration, and the outdoor environmental parameters further include the outdoor ozone concentration. The real-time environmental data accordingly includes the indoor volatile organic compound concentration and the outdoor ozone concentration.

[0058] The control module converts the dynamic fresh air ratio parameters into control commands and sends them to the central air conditioning controller to adjust the opening of the return air valve and the fresh air valve.

[0059] In a specific embodiment of the present invention, the step of converting the dynamic fresh air ratio parameter into a control command includes: mapping the dynamic fresh air ratio parameter into a control signal according to a device mapping table that defines the signal protocol of the central air conditioning controller.

[0060] The control signals are encapsulated into data packets conforming to the Internet of Things (IoT) communication protocol to generate the control commands.

[0061] In a specific embodiment of the present invention, after the calculation performed by the dynamic weight adjustment model, the method further includes: obtaining actual indoor environmental parameters after the control command is executed.

[0062] The actual indoor environmental parameters are compared with the target parameters that characterize the ideal indoor environment, and the deviation of each key control index in the actual indoor environmental parameters is calculated.

[0063] It should be noted that the target parameters representing the ideal indoor environment refer to a set of benchmark reference values ​​corresponding to the actual indoor environmental parameters, set according to indoor air quality standards, human thermal comfort specifications, and actual application scenario requirements, in order to ensure the health and comfort of indoor occupants and the energy efficiency of the central air conditioning system. These values ​​are used to compare with the actual monitored indoor environmental parameters, calculate control deviations, and provide feedback to optimize the dynamic weight adjustment model. Furthermore, the target parameters can be dynamically adapted according to specific application scenarios, user needs, or industry standards updates to ensure consistency with actual control requirements and provide accurate and reasonable benchmarks for calculating control deviations.

[0064] Specifically, the method for calculating the deviation of each key control indicator is as follows: .

[0065] in, This represents the deviation of the calculated i-th key control indicator. This represents the i-th key control indicator among the actual indoor environmental parameters. This represents the i-th target parameter characterizing the ideal indoor environment, where i is the number of the key control indicator. Let be the dynamic weight of the i-th key control indicator, i=1,2,...,n.

[0066] It should be noted that the dynamic weights of the key control indicators are consistent with the weight priorities in the dynamic weight adjustment model described above.

[0067] Based on the deviation of each key control indicator, the internal parameters of the dynamic weight adjustment model are updated.

[0068] Specifically, based on the deviation of each key control indicator, the dominant deviation key control indicator is identified, and a preset deviation-internal parameter mapping rule library is invoked to match and obtain an internal parameter mapping set. The internal parameter mapping set includes internal parameter types and adjustment amounts, which are then used to update the internal parameters of the dynamic weight adjustment model. For example, if the indoor CO2 concentration deviation is greater than threshold A and the duration exceeds T1, the CO2 control weight benchmark amount X% is increased. If the indoor PM2.5 concentration deviation is greater than threshold B and the outdoor PM2.5 concentration is high, the fresh air introduction weight benchmark amount Y is decreased.

[0069] It should be noted that the internal parameters are the underlying settings that determine how the dynamic control weights are generated. These include the baseline value for CO2 control weight, the baseline value for fresh air introduction weight, the correspondence rules / coefficients between features and weights, and the mapping rules between deviations and parameter adjustments. The correspondence rules / coefficients between features and weights can be found in a CO2 control weight adjustment table corresponding to a personnel density feature interval, or a mathematical expression showing how CO2 control weights change with personnel density features. Similarly, outdoor air quality features and fresh air introduction weights also have similar correspondence tables or expressions.

[0070] The control decisions of this invention are not based on isolated real-time data, but rather on the analysis of historical data and external information, achieving predictive and forward-looking control. The system can anticipate future changes in occupancy and outdoor air quality trends, and proactively plan and adjust control strategies, effectively avoiding the lag inherent in traditional reactive control. This results in a more stable and efficient system operation, further enhancing the stability and comfort of the indoor environment.

[0071] This invention constructs a closed-loop feedback system with adaptive learning capabilities. By continuously comparing the control effect with the expected target, the system can automatically identify and quantify decision deviations, and iteratively optimize the internal model parameters accordingly. This self-improvement mechanism enables the system to continuously adapt to the long-term evolution of building characteristics, seasonal changes, and user behavior patterns, ensuring the long-term optimality of the control strategy and achieving a high degree of automation and intelligent management.

[0072] It's important to note that this improvement significantly enhances the system's environmental awareness and control precision. By introducing two key pollutant indicators—indoor volatile organic compound (VOC) concentration and outdoor ozone concentration—the system's decision-making is no longer limited to traditional CO2 and particulate matter. This allows the system to identify and address more complex air quality issues, such as harmful gases released from building materials or outdoor ozone pollution generated by photochemical reactions. Therefore, the system's control objective has evolved from simply improving comfort and reducing energy consumption to comprehensively ensuring the health and safety of indoor occupants. This multi-pollutant synergistic control strategy results in an air quality optimization effect and health protection level far exceeding the sum of effects achievable by controlling a single or a few pollutants independently.

[0073] Reference Figure 2 As shown, the second aspect of the present invention provides a method for executing the cloud computing-based Internet of Things central air conditioning intelligent control system described in the present invention, comprising: step one, acquiring indoor environmental parameters and outdoor environmental parameters, and generating real-time environmental data.

[0074] Step 2: Send the real-time environmental data to the cloud computing platform for multi-source data fusion processing to generate an environmental state vector.

[0075] Step 3: Based on the environmental state vector, perform calculations using a dynamic weight adjustment model to generate dynamic fresh air ratio parameters.

[0076] Step 4: Convert the dynamic fresh air ratio parameters into control commands and send them to the central air conditioning controller to adjust the opening of the return air valve and the fresh air valve.

[0077] This invention overcomes the technical shortcomings of traditional central air conditioning systems, which use a fixed fresh air ratio, leading to poor indoor air quality or energy waste. By constructing a control system capable of real-time sensing, intelligent analysis, and dynamic response, this method can continuously and precisely adjust the fresh air intake based on various dynamic changes, such as indoor occupancy, indoor air pollutant levels, and outdoor air quality. It no longer blindly maintains a fixed ventilation ratio but achieves intelligent trade-offs and dynamic optimization between ensuring indoor air quality and saving energy consumption. Therefore, this method can ensure a consistently healthy and comfortable indoor environment while minimizing unnecessary energy consumption, significantly improving the overall operational efficiency and intelligence level of the central air conditioning system.

[0078] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0079] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0080] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

[0081] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A cloud-based IoT-based intelligent control system for central air conditioning, characterized in that: include: The environmental data acquisition module is used to acquire indoor and outdoor environmental parameters and generate real-time environmental data. The environmental data processing module is used to send the real-time environmental data to the cloud computing platform for multi-source data fusion processing to generate an environmental state vector. The fresh air ratio generation module is used to generate dynamic fresh air ratio parameters based on the environmental state vector by performing calculations through a dynamic weight adjustment model. The control module converts the dynamic fresh air ratio parameters into control commands and sends them to the central air conditioning controller to adjust the opening of the return air valve and the fresh air valve.

2. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 1, characterized in that, The content of the generated real-time environmental data includes: Indoor environmental parameters are obtained by monitoring indoor CO2 concentration, indoor temperature, indoor humidity, and number of people through an Internet of Things (IoT) sensor network. Outdoor environmental parameters are obtained by monitoring outdoor CO2 and particulate matter concentrations through an Internet of Things (IoT) sensor network. By integrating the indoor environmental parameters and the outdoor environmental parameters, the real-time environmental data is generated. ; in, Represents indoor CO2 concentration; Represents indoor temperature; Represents indoor humidity; Number of representatives; Represents outdoor CO2 concentration; Represents outdoor PM2.5 concentration; This represents the outdoor temperature.

3. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 2, characterized in that, The generated environment state vector includes the following: The number of people and the area of ​​the air conditioning monitoring area are extracted from the real-time environmental data to calculate the personnel density characteristics. Outdoor CO2 concentration and outdoor particulate matter concentration are extracted from the real-time environmental data, normalized, and then weighted to generate outdoor air quality characteristics. The environmental state vector is generated by combining the personnel density characteristics, the outdoor air quality characteristics, and the indoor CO2 concentration extracted from the real-time environmental data. ; in, For population density characteristics, Characteristics of outdoor air quality This represents the characteristics of indoor CO2 concentration.

4. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 3, characterized in that, The calculations performed using the dynamic weight adjustment model include: Based on the personnel density characteristics in the environmental state vector, a CO2 control weight is dynamically adjusted to characterize the priority of CO2 control. Based on the outdoor air quality characteristics in the environmental state vector, a fresh air introduction weight is dynamically adjusted to characterize the suitability of introducing fresh air. By combining the adjusted CO2 control weights and the fresh air introduction weights, the indoor CO2 concentration in the environmental state vector is calculated to generate the dynamic fresh air ratio parameter.

5. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 4, characterized in that, The calculations performed using the dynamic weight adjustment model also include: Acquire historical environmental data and external weather forecast data; Based on the historical environmental data and external weather forecast data, a future population density trend and a future outdoor air quality trend are generated. Based on the future population density trend and the future outdoor air quality trend, the CO2 control weight and the fresh air introduction weight in the dynamic weight adjustment model are proactively adjusted and updated into the parameter set of the dynamic weight adjustment model.

6. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 1, characterized in that, Following the content calculated using the dynamic weight adjustment model, the following also includes: After the control command is executed, the actual indoor environmental parameters are obtained; The actual indoor environmental parameters are compared with the target parameters characterizing the ideal indoor environment, and the deviation of each key control index in the actual indoor environmental parameters is calculated. Based on the deviation of each key control indicator, the internal parameters of the dynamic weight adjustment model are updated.

7. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 1, characterized in that, The process of converting the dynamic fresh air ratio parameter into a control command includes: Based on the device mapping table that defines the signal protocol of the central air conditioning controller, the dynamic fresh air ratio parameter is mapped into a control signal; The control signals are encapsulated into data packets conforming to the Internet of Things (IoT) communication protocol to generate the control commands.

8. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 1, characterized in that, The indoor environmental parameters also include the indoor volatile organic compound concentration, and the outdoor environmental parameters also include the outdoor ozone concentration; the real-time environmental data accordingly includes the indoor volatile organic compound concentration and the outdoor ozone concentration.

9. The cloud computing-based IoT-based intelligent control system for central air conditioning as described in claim 1, characterized in that, The dynamic weight adjustment model is calculated in the following manner: The numerical features in the environmental state vector, along with the adjusted CO2 control weights and fresh air intake weights, are converted into fuzzy linguistic variables. Among them, the CO2 control weight corresponds to the CO2 control priority fuzzy variable, and the fresh air introduction weight corresponds to the fresh air suitability fuzzy variable. Fuzzy reasoning is performed on the above fuzzy linguistic variables based on a rule base containing expert rules. During the reasoning process, the trigger weights of the corresponding rules are adjusted according to the membership degree of the CO2 control priority and the fresh air suitability fuzzy variables. The fuzzy inference output after weight adjustment is defuzzified to generate the dynamic fresh air ratio parameter.

10. A method for implementing the cloud computing-based Internet of Things (IoT) intelligent control system for central air conditioning as described in any one of claims 1-9, characterized in that, include: Step 1: Obtain indoor and outdoor environmental parameters and generate real-time environmental data; Step 2: Send the real-time environmental data to the cloud computing platform for multi-source data fusion processing to generate an environmental state vector; Step 3: Based on the environmental state vector, perform calculations using a dynamic weight adjustment model to generate dynamic fresh air ratio parameters; Step 4: Convert the dynamic fresh air ratio parameters into control commands and send them to the central air conditioning controller to adjust the opening of the return air valve and the fresh air valve.

Images