Heating ventilation air conditioner control method, system and equipment based on dynamic heat load prediction

Abstract

The invention provides a heating ventilation air conditioner control method, system and device based on dynamic heat load prediction and a storage medium. The method comprises the following steps: acquiring indoor individual physiological data, environmental parameters and regional personnel distribution data in real time; determining a real-time individual metabolic rate equivalent based on the individual physiological data and the environmental parameters; aggregating the individual metabolic rate equivalents according to the regional personnel distribution data, determining the total heat load and the total heat load change rate of each indoor region, and decomposing the total heat load into a sensible heat load and a latent heat load; and on the basis of the sensible heat load, the latent heat load and the total heat load change rate, air supply temperature, air supply amount and humidity control instructions of the heating ventilation air conditioning system for feed-forward adjustment are generated. According to the technical scheme, dynamic thermal load prediction based on individual physiological data and environmental parameters can be achieved, the indoor total thermal load is quantified in real time, and the feedforward adjustment control instruction of the heating ventilation air conditioning system is generated.

Description

Technical Field

[0001] The present invention relates to the field of HVAC control, and in particular to a HVAC control method, system, device and storage medium based on dynamic heat load prediction. Background Art

[0002] With the increasing dynamics of human activity in indoor environments, existing HVAC control strategies face challenges. While well-established, traditional fixed-temperature control strategies lack the ability to detect the actual presence and activity of people indoors. In locations with high occupancy rates, such as gyms during peak hours, fixed-temperature control can easily lead to overheating or overcooling, reducing comfort levels. Furthermore, in sparsely populated areas, this can waste energy.

[0003] To address this issue, feedback control strategies based on environmental sensors are widely used, with adjustments based on indoor temperature sensors. However, the inherent response lag of this technology limits its ability to instantly regulate human thermal comfort. When human activity generates additional heat, it takes time for the air temperature to change sufficiently for the sensor to capture it. During this time, the human body may already be experiencing discomfort. In recent years, indoor fresh air control based on carbon dioxide concentration has gradually gained attention. This strategy infers the number of indoor occupants by monitoring carbon dioxide concentration and adjusts the fresh air volume, but it still has shortcomings in thermal comfort regulation. Changes in carbon dioxide concentration are indirect and have a lag, making it difficult to promptly reflect instantaneous changes in the intensity of human activity. Furthermore, carbon dioxide cannot quantify human load, nor can it distinguish between sensible heat generated by exercise and latent heat generated by sweat evaporation. This has significant limitations in assessing human heat production during high-intensity activities. Summary of the Invention

[0004] The purpose of the present invention is to provide a HVAC control method, system, device and storage medium based on dynamic heat load prediction to solve the problems of traditional HVAC control such as delayed response, insufficient thermal comfort and energy waste under dynamic changes in personnel activities.

[0005] In a first aspect, the present invention provides a HVAC control method based on dynamic heat load prediction, comprising the following steps: Real-time acquisition of indoor individual physiological data, environmental parameters, and regional personnel distribution data; Determining a real-time individual metabolic rate equivalent based on the individual physiological data and environmental parameters; Aggregating the individual metabolic rate equivalents according to the regional personnel distribution data, determining the total heat load and the total heat load change rate of each indoor area, and decomposing the total heat load into sensible heat load and latent heat load; Based on the sensible heat load, latent heat load and the total heat load change rate, supply air temperature, supply air volume and humidity control instructions for the HVAC system for feedforward regulation are generated.

[0006] Optionally, the specific steps of determining the real-time individual metabolic rate equivalent based on the individual physiological data and environmental parameters include: Based on the environmental parameters, evaluating the impact of the indoor environment on the individual metabolic rate to obtain an environmental correction factor; Identify individual exercise types and determine corresponding baseline metabolic equivalents and real-time baseline heart rate values ​​based on the exercise types; Determining individual exercise intensity based on the real-time baseline heart rate value and the corresponding baseline heart rate interval; The real-time individual metabolic rate equivalent is calculated based on the environmental correction factor, the baseline metabolic equivalent and the individual exercise intensity.

[0007] Optionally, the calculation formula for the individual metabolic rate equivalent is: ; in, is the metabolic rate of a single individual at an instant; is the environmental correction factor; is the individual exercise intensity; Indicates that the motion type is The individual heart rate baseline value is calculated when Indicates that the motion type is The actual benchmark value corresponding to the actual activity metabolic rate benchmark table.

[0008] Optionally, the specific steps of identifying the individual's movement type include: Acquiring three-axis acceleration data of a wearable device worn by an individual, and performing feature extraction on the three-axis acceleration data; Inputting the extracted features into a pre-trained classification model to obtain motion type information based on the three-axis acceleration data; The individual selects the current activity type from a preset activity list through the software interface, and obtains the exercise type information based on the user's selection; The final individual motion type is determined by combining the motion type information based on the three-axis acceleration data and the motion type information based on the user's selection.

[0009] Optionally, the specific steps of aggregating the individual metabolic rate equivalents according to the regional personnel distribution data, determining the total heat load and the total heat load change rate of each indoor area, and decomposing the total heat load into sensible heat load and latent heat load include: Based on the regional personnel distribution data, the individual metabolic rate equivalents of each person in the same area are aggregated to obtain the total heat load of each indoor area; Calculating the rate of change of the total heat load of each indoor area over time to obtain the total heat load change rate, so as to quantify the change direction and speed of the total heat load; calculating the evaporative heat dissipation required by the human body and the maximum evaporative heat dissipation capacity of the region based on the total heat load and environmental parameters, and comparing the evaporative heat dissipation required by the human body with the maximum evaporative heat dissipation capacity of the region to obtain a final latent heat load; The sensible heat load of each zone is obtained by subtracting the latent heat load from the total heat load.

[0010] Optionally, the specific steps of generating the supply air temperature, supply air volume and humidity control instructions for the HVAC system for feedforward regulation based on the sensible heat load, latent heat load and the total heat load change rate include: Determining a base supply air temperature offset based on the sensible heat load and the current supply air temperature of the HVAC system; Determining a basic dew point humidity offset based on the latent heat load and the current air supply volume of the HVAC system; Based on the total heat load change rate, the basic supply air temperature offset and the basic dew point humidity offset are corrected by a dynamic gain function to obtain a final supply air temperature offset and a final dew point humidity offset; Combining the supply air temperature offset, the dew point moisture offset and the real-time status of the HVAC system, a supply air temperature, supply air volume and humidity control instruction for the HVAC system for feedforward regulation is generated.

[0011] Optionally, the HVAC control method further includes: Detect indoor environment deviations caused by unpredictable disturbances or model errors, and generate feedback correction instructions based on the detection results; The feedback correction instruction and the air supply temperature, air supply volume and humidity control instruction of the HVAC system for feedforward regulation are combined to generate a final HVAC system regulation instruction.

[0012] In a second aspect, the present invention provides a HVAC control system based on dynamic heat load prediction, comprising: Data acquisition module, used to obtain indoor individual physiological data, environmental parameters and regional personnel distribution data in real time; A human metabolic rate calculation module, configured to determine a real-time individual metabolic rate equivalent based on the individual physiological data and environmental parameters; a load prediction module for aggregating the individual metabolic rate equivalents based on the regional personnel distribution data, determining the total heat load and the rate of change of the total heat load for each indoor area, and decomposing the total heat load into sensible heat load and latent heat load; The control module is used to generate air supply temperature, air supply volume and humidity control instructions for the HVAC system for feedforward regulation based on the sensible heat load, latent heat load and the total heat load change rate.

[0013] In a third aspect, the present invention provides a device comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned HVAC control method.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned HVAC control method are implemented.

[0015] The present invention's solution, by acquiring real-time indoor individual physiological data, environmental parameters, and regional occupancy data, determines the total heat load and its rate of change for each zone, decomposing it into sensible and latent heat loads. This accurately captures the dynamics of indoor occupant activity and heat and humidity loads. Compared to traditional control methods that rely on temperature or carbon dioxide concentration, the present invention's technical solution offers greater real-time performance and accuracy, directly reflecting the combined effects of occupant number and activity intensity. This provides a highly accurate data foundation for subsequent HVAC control, significantly enhancing the foresight and proactive nature of control strategies.

[0016] Furthermore, by decoupling the heat load to obtain the latent heat load and the sensible heat load, the basic control set points of the supply air temperature and humidity are determined respectively, and the dynamic gain function is introduced by using the total heat load change rate for correction, thereby forming a forward-looking supply air temperature offset and dew point moisture content offset. In addition, the present invention forms the final HVAC adjustment instruction by combining the feedforward control instruction based on prediction with the feedback correction instruction generated by the environmental deviation detected in real time, thereby achieving the coordinated work of the rapid response of the feedforward adjustment and the fine compensation of the feedback correction. The method of the present invention can not only respond to the sudden changes in the number of indoor people and activity intensity in advance, suppress the adjustment lag of environmental parameters, but also avoid energy waste caused by excessive or insufficient adjustment, while significantly improving the indoor thermal comfort, maintaining the high efficiency and stability of the HVAC system operation.

[0017] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of a HVAC control method based on dynamic heat load prediction according to an embodiment of the present invention is shown; Figure 2 Shown Figure 1 Schematic flow chart of determining a real-time individual metabolic rate equivalent based on individual physiological data and environmental parameters in step S200; Figure 3 Shown Figure 2 Schematic flow chart of identifying individual movement type in step S220; Figure 4 Shown Figure 1 A schematic flow chart of step S300 aggregating individual metabolic rate equivalents based on regional occupant distribution data, determining the total heat load and total heat load change rate of each indoor area, and decomposing the total heat load into sensible heat load and latent heat load; Figure 5 Shown Figure 1 A schematic flow chart of generating control instructions for supply air temperature, supply air volume, and humidity of a HVAC system for feedforward regulation based on the sensible heat load, latent heat load, and total heat load change rate in step S400; Figure 6 A structural block diagram of a HVAC control system based on dynamic heat load prediction according to an embodiment of the present invention is shown; Figure 7 A structural block diagram of a HVAC control device based on dynamic heat load prediction according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. It will be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some, rather than all, structures related to the present application are shown in the accompanying drawings. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0020] As used herein, the terms "comprise," "comprising," and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0021] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] Figure 1 FIG1 shows a schematic flow chart of a HVAC control method based on dynamic heat load prediction according to an embodiment of the present invention. Figure 1 As shown, the HVAC control method includes: Step S100: Acquire indoor individual physiological data, environmental parameters, and regional personnel distribution data in real time.

[0023] In this step, through the real-time collection of multi-dimensional data, a comprehensive understanding of indoor occupant dynamics and environmental conditions is achieved, laying the foundation for subsequent heat load calculations. In some embodiments, individual physiological data can be acquired through wearable devices such as smartwatches, wristbands, or finger rings, reflecting individual thermophysiological characteristics such as heart rate, skin temperature, blood oxygen saturation, and exercise status. Environmental parameter data is continuously monitored by indoor temperature, humidity, carbon dioxide, and other air quality sensors to describe the overall environmental conditions of the building space. Regional occupant distribution data can be acquired in real time using a contactless positioning method based on Bluetooth beacons, accurately reflecting the number and distribution of occupants in different functional areas (such as the strength, aerobic, and yoga areas in a gym). By simultaneously acquiring these three types of data, reliable and detailed input information can be provided for the calculation of metabolic rate equivalents and the prediction of dynamic heat load in subsequent steps, thus avoiding the lag and distortion problems caused by relying on a single measurement indicator.

[0024] Step S200 : determining a real-time individual metabolic rate equivalent based on individual physiological data and environmental parameters.

[0025] In this step, the individual's real-time metabolic rate equivalent is dynamically calculated by combining individual physiological signals with environmental factors. Compared to methods that rely on empirical estimates or fixed metabolic assumptions, the processing in step S200 accurately characterizes the instantaneous heat production levels of different people in different environments and automatically adjusts to changes in exercise intensity. This not only improves the accuracy of heat load prediction but also provides high-resolution individual input for subsequent partition aggregation, enabling more precise adjustment of control strategies to actual activity conditions.

[0026] Step S300 : Aggregate individual metabolic rate equivalents based on regional personnel distribution data to determine the total heat load and total heat load change rate of each indoor area, and decompose the total heat load into sensible heat load and latent heat load.

[0027] In this step, the introduction of the rate of change reflects the trends and dynamic characteristics of load increases and decreases, helping to predict fluctuations in cooling / heating demand. Separating sensible heat from latent heat creates the conditions for subsequent independent control of supply air temperature and humidity, enabling the system to more specifically address the increase in sensible heat caused by high-intensity activity or the increase in latent heat load caused by excessive sweating, thus balancing comfort and control efficiency.

[0028] Step S400 : Based on the sensible heat load, latent heat load and total heat load change rate, generate control instructions for the supply air temperature, supply air volume and humidity of the HVAC system for feedforward regulation.

[0029] In this step, the sensible heat load, latent heat load, and their rates of change are integrated to generate the supply air temperature, air volume, and humidity control commands required for feedforward regulation, enabling proactive response. By directly converting load forecast results into executable control commands, the system can intervene before changes in human activity cause environmental deviations, preventing overshoots in room temperature or humidity and significantly reducing response lag. Furthermore, incorporating the dynamic load change rate into the calculation makes the control output more stable and sensitive, ensuring comfort while reducing energy waste and improving the efficiency and stability of the HVAC system.

[0030] According to the above embodiment, by acquiring real-time indoor individual physiological data, environmental parameters, and regional occupant distribution data, the total heat load and its rate of change for each area are determined, and this is decomposed into sensible heat load and latent heat load. This allows for precise characterization of indoor occupant activity and the dynamic changes in heat and humidity loads. Compared to traditional control methods that rely on temperature or carbon dioxide concentration, the technical solution of the present invention offers greater real-time performance and accuracy, directly reflecting the combined effects of occupant number and activity intensity. This provides a highly accurate data foundation for subsequent HVAC control, significantly enhancing the foresight and proactive nature of control strategies.

[0031] Figure 2 Shown Figure 1Schematic flow chart of determining the real-time individual metabolic rate equivalent based on individual physiological data and environmental parameters in step S200. Figure 2 As shown, step S200 includes: Step S210 : Based on the environmental parameters, the impact of the indoor environment on the individual metabolic rate is evaluated to obtain an environmental correction factor.

[0032] In this step, the actual impact of the environment on the human metabolic rate is calculated by comprehensively evaluating environmental parameters such as indoor temperature and humidity. In a hot and humid environment, the human body needs to make additional physiological efforts to maintain body temperature, such as increasing skin blood flow and increasing sweating rate. This will increase the load on the cardiovascular system, resulting in higher heart rate and energy consumption at the same exercise output power. By quantifying these physiological changes as environmental correction factors, the differences in individual metabolic levels under different environmental conditions can be accurately reflected, providing a more realistic and refined basis for subsequent metabolic rate equivalent calculations.

[0033] In one embodiment, the calculation formula of the environmental correction factor is: ; Among them, k e It represents the environmental correction factor for the quantification of exercise intensity. The model takes 1 as the baseline value, which corresponds to the standard metabolic level in a comfortable environment. When the environmental conditions deviate from the comfort zone, it will cause k e >1; is the temperature weight coefficient; T is the actual temperature measured by the environmental monitoring sensor; T C is the comfort reference temperature; is the humidity weight coefficient; RH is the relative humidity measured by the environmental monitoring sensor; RH C It is the comfort benchmark relative humidity.

[0034] Step S220: Identify the individual's exercise type and determine the corresponding baseline metabolic equivalent and real-time baseline heart rate value according to the exercise type.

[0035] In this step, the heat production characteristics corresponding to different exercise types vary significantly. For example, aerobic exercise and strength training have different heat generation mechanisms. By identifying individual exercise types, it can be ensured that subsequent calculations are based on baseline data that conforms to the actual exercise pattern, thereby improving the accuracy of metabolic rate estimation.

[0036] Step S230: determining individual exercise intensity based on the real-time reference heart rate value and the corresponding reference heart rate interval.

[0037] In this step, even when performing the same type of activity (e.g., aerobic training like running), the actual metabolic output of different individuals can vary significantly due to factors such as exercise pace, fitness level, fatigue status, and emotional state. Heart rate, as an ideal physiological indicator to reflect these differences, can objectively reflect the load level on the cardiovascular system. To ensure the accuracy of exercise intensity assessment, the collected heart rate data must be individualized and standardized. By mapping the real-time heart rate to the individual's effective range from resting to maximum heart rate, the exercise intensity can be quantified and the degree to which the cardiovascular system is mobilized can be truly reflected.

[0038] In one embodiment, the formula for quantifying individual exercise intensity is: ; Among them, HRR stands for heart rate reserve, which is calculated by the difference between maximum heart rate and resting heart rate. It is used to quantify an individual's adjustable heart rate range and divide exercise intensity intervals accordingly; HR n Indicates the real-time measured heart rate value; HR rest Indicates the heart rate value of an individual in an awake and inactive state; HR max It indicates the highest heart rate an individual can reach during extreme exercise, and can usually be estimated using the empirical formula of "220-age".

[0039] Step S240 , calculating the real-time individual metabolic rate equivalent based on the environmental correction factor, the baseline metabolic equivalent, and the individual exercise intensity.

[0040] In this step, the environmental correction factor, baseline metabolic equivalent, and individual exercise intensity are integrated to calculate the individual's instantaneous metabolic rate equivalent. This comprehensive calculation not only reflects the individual's theoretical metabolic level at a specific exercise intensity but also takes into account environmental influences and individual differences, resulting in a highly realistic metabolic rate assessment. This result can be directly used in indoor dynamic heat load modeling, improving the timeliness and accuracy of predictions.

[0041] In one embodiment, the calculation formula for individual metabolic rate equivalent is: ; in, is the metabolic rate of a single individual at an instant; is the environmental correction factor; is the individual exercise intensity; Indicates that the motion type is The individual heart rate baseline value is calculated when Indicates that the motion type is The actual benchmark value corresponding to the actual activity metabolic rate benchmark table.

[0042] Figure 3 Shown Figure 2 Schematic flow chart of identifying individual movement type in step S220. Figure 3 As shown, step S220 includes: Step S221: Acquire three-axis acceleration data of the wearable device worn by the individual, and perform feature extraction on the three-axis acceleration data.

[0043] In step S222 , the extracted features are input into a pre-trained classification model to obtain motion type information based on the three-axis acceleration data.

[0044] In the above steps S221 and S222, by obtaining the three-axis acceleration data of the wearable device worn by the individual and performing feature extraction on it, the dynamic patterns and changing trends of the user's movement in different directions can be captured. This process converts the raw motion data into a set of key motion features by real-time analysis of the three-axis acceleration signal, and automatically identifies it in combination with a pre-trained machine learning model. The model can output activity labels such as "sitting", "walking" or "running" based on these features, thereby providing a reliable input basis for subsequent metabolic rate calculations. Its mathematical formula is expressed as: ; ; Among them, AAC represents the three-axis acceleration raw data collected by the wearable device, which constitutes a three-dimensional vector at any time Used to characterize the individual's motion state in different directions. Represents the recognition time; It is expressed as a feature extraction function, which is used to transform the messy and redundant information in the original acceleration signal into representative key feature indicators; Represents a classification function that identifies and classifies the extracted feature vectors, corresponding to a pre-trained machine learning classification model; represents the final activity label output by the classification model at time t, such as "sitting", "walking" or "running".

[0045] In step S223, the individual selects a current activity type from a preset activity list through a software interface to obtain exercise type information based on the user's selection.

[0046] In this step, the user actively selects the type of activity they are performing through a software interface (e.g., a mobile app or wearable device screen). Users can directly select their current activity from a list of pre-set activities (such as "yoga," "spinning," or "strength training"), and the system records this selection as the exercise type. This method, which relies on active user interaction, ensures absolute accuracy in recognition results and can effectively distinguish specific exercise types with similar movement patterns but significantly different metabolic levels.

[0047] Step S224 , combining the motion type information based on the three-axis acceleration data and the motion type information based on the user's selection to determine a final individual motion type.

[0048] In this step, the system combines the automatic recognition results based on triaxial acceleration data with the user's manual selection information to determine the final individual exercise type label. Subsequently, the built-in actual activity metabolic rate benchmark table is queried based on the label to obtain the corresponding baseline metabolic equivalent (MET) and baseline heart rate value. The metabolic equivalents of different activities vary significantly. For example, the metabolic equivalent of walking is approximately 2.0 to 3.8 depending on the pace, gymnastics is 3.0 to 4.0, and basketball is 5.0 to 7.6. In this way, the accuracy of exercise type identification is ensured, and reliable basic data is provided for subsequent metabolic rate calculation and exercise intensity analysis.

[0049] Figure 4 Shown Figure 1 The schematic flow chart of step S300 is to aggregate the individual metabolic rate equivalent according to the regional personnel distribution data, determine the total heat load and the total heat load change rate of each indoor area, and decompose the total heat load into sensible heat load and latent heat load. Figure 4 As shown, step S300 includes: In step S310 , based on the regional personnel distribution data, the individual metabolic rate equivalents of each person in the same area are aggregated to obtain the total heat load of each indoor area.

[0050] In this step, by obtaining the real-time distribution of people in each area, the system can identify the people in each area and convert each person's metabolic equivalent into an absolute heat production rate (in watts) to quantify the total human heat source intensity in the area. Specifically, the DuBois formula is first used to calculate the individual's body surface area, and then the conversion coefficient is used to convert the individual's metabolic equivalent into an absolute heat production rate. The specific formula is as follows: ; ; Where A represents the individual body surface area, W i represents the weight of individual i, H i represents the height of individual i, represents the absolute metabolic heat production rate of individual i at time t, represents the metabolic rate of a single individual at instantaneous time t.

[0051] Then, the absolute heat production rates of all people in the same area are arithmetically summed to obtain the total heat load of the area. The specific formula is as follows: ; in, represents the current total metabolic heat production rate of region z at time t; represents the absolute metabolic heat production rate of individual i at time t; It represents the set of all individuals i located in area z at time t. This set is dynamically updated by the real-time positioning system and changes in real time as people enter and leave the area.

[0052] This step S310 can accurately summarize the individual's dynamic physiological information at the regional level, providing a reliable data basis for subsequent heat load analysis and feedforward adjustment of the HVAC system, while also achieving a quantitative reflection of the heat load differences in different regions.

[0053] Step S320 , calculating the rate of change of the total heat load of each indoor area over time, and obtaining the total heat load change rate, so as to quantify the change direction and speed of the total heat load.

[0054] In this step, the rate and direction of change in the total heat load are quantified by calculating the change in the total metabolic heat production rate over time for each zone. Specifically, the backward difference method is used to calculate the time derivative of the total metabolic heat production rate, thereby obtaining the load change rate. When the total heat load change rate in a particular zone reaches a large positive value, it indicates that the cooling load in that area is about to increase rapidly. The system can predict and adjust the air conditioning output accordingly, achieving proactive control of environmental conditions, improving indoor comfort, and avoiding energy waste.

[0055] In one embodiment, the total heat load rate of change is given by: ; in, represents the rate of change of the total heat load of zone z over time; represents the total metabolic heat production rate of region z at time t; Indicates the regional total metabolic heat production rate in the previous calculation cycle (time t-Δt); Represents the calculation time step, that is, the frequency interval of data sampling and calculation.

[0056] Step S330 , based on the total heat load and environmental parameters, the evaporative heat dissipation required by the human body and the maximum evaporative heat dissipation capacity of the region are calculated, and the evaporative heat dissipation required by the human body and the maximum evaporative heat dissipation capacity of the region are compared to obtain the final latent heat load.

[0057] Step S340: Subtract the latent heat load from the total heat load to obtain the sensible heat load of each zone.

[0058] In indoor environments, the total heat generated by the human body is released as both sensible and latent heat. HVAC systems must adjust for these two types of loads separately. First, the maximum evaporative heat dissipation capacity of the human body through the skin is calculated based on current environmental parameters. The latent heat dissipation required to maintain thermal equilibrium is also assessed. The latent heat load is calculated as the smaller of the two, ensuring the air conditioning system does not overestimate the latent heat demand. The actual latent heat load is then subtracted from the total body heat, resulting in the sensible heat load as the remainder. This ensures a reasonable division between the sensible and latent heat loads, providing a precise control basis for subsequent feedforward regulation.

[0059] First, define the total heat dissipation generated by the human body, which is the total heat dissipation demand of the area: ; in, is the predicted total regional cooling demand; The current total heat load of zone z at time t.

[0060] In one embodiment, the maximum evaporative heat dissipation capacity of a region is calculated as follows: ; in, Indicates the maximum evaporative heat dissipation capacity of the region, that is, the maximum latent heat that the environment can take away; It represents the evaporative heat transfer coefficient between the wet skin surface and the surrounding air. This coefficient is an empirical value calibrated based on experimental data and is combined with the air flow rate to determine the overall evaporative heat transfer efficiency. Indicates the average air velocity in the area; represents the saturated water vapor partial pressure at the assumed skin temperature; It represents the water vapor partial pressure of the regional ambient air, which is calculated from the regional ambient temperature T and the regional ambient humidity RH; The total body surface area of ​​all people in the area.

[0061] In one embodiment, the calculation formula for the evaporative heat dissipation required by the human body is: ; ; in, Indicates the amount of evaporative heat dissipation required by the human body to maintain thermal balance; represents the predicted total cooling demand for the region; Indicates the maximum sensible heat that the environment can remove; It represents the combined heat transfer coefficient between the outer surface of the human body (clothing) and the entire indoor environment, and its value is 7.2W / (m 2 K); Represents the total body surface area of ​​all people in the area; Indicates the average skin temperature, calculated at 35°C; Indicates the dry-bulb temperature of zone z.

[0062] In one embodiment, the final latent heat load and sensible heat load are determined by the formula: ; ; in, represents the final predicted regional latent heat load; Indicates the amount of evaporative heat dissipation required by the human body to maintain thermal balance; Indicates the maximum latent heat that the environment can take away; Indicates physiological basis respiratory latent heat; represents the final predicted zone sensible heat load; Represents the total projected cooling demand for the zone.

[0063] Figure 5 Shown Figure 1 The schematic flow chart of step S400 of generating the supply air temperature, supply air volume and humidity control instructions for the HVAC system for feedforward regulation based on the sensible heat load, latent heat load and total heat load change rate is shown. Figure 5 As shown, step S400 includes: Step S410 : determining a basic supply air temperature offset based on the sensible heat load and the current supply air temperature of the HVAC system.

[0064] In this step, the system preliminarily sets the supply air temperature based on the calculated sensible heat load for each zone and the current HVAC system supply air temperature. Sensible heat load primarily reflects the perceived heat demand of the human body and the environment. By determining the base supply air temperature offset with reference to the current supply air temperature, the air conditioning system ensures that the appropriate heat adjustment is immediately provided during the feedforward control phase. This allows for a rapid response to indoor temperature demands, improving occupant thermal comfort and reducing comfort fluctuations caused by temperature lag.

[0065] Step S420 : determining a basic dew point humidity offset based on the latent heat load and the current air flow of the HVAC system.

[0066] In this step, the latent heat load is processed and the base dew point humidity offset is determined based on the HVAC system's current air flow rate. Latent heat load primarily corresponds to the amount of heat lost through evaporation of sweat, and its regulation is closely related to air humidity. By accurately calculating the base dew point humidity offset, the system can ensure that indoor humidity is controlled within a reasonable range, meeting the human body's evaporative heat dissipation needs while avoiding discomfort and energy waste caused by excessively high or low humidity.

[0067] Step S430 : Based on the total heat load change rate, the basic supply air temperature offset and the basic dew point humidity offset are corrected by a dynamic gain function to obtain a final supply air temperature offset and a final dew point humidity offset.

[0068] In this step, the base supply air temperature offset and base dew point humidity offset are corrected using a dynamic gain function based on the calculated total heat load change rate to obtain the final supply air temperature offset and dew point humidity offset. By quantifying the direction and rate of heat load change, this step enables proactive optimization of air conditioning settings, allowing air supply conditions to proactively adapt to changes in the indoor environment, further improving comfort and reducing energy consumption fluctuations.

[0069] In one embodiment, the specific calculation formula of the offset is as follows: ; ; in, Indicates the final supply air temperature offset; Indicates the basic supply air temperature offset; Indicates the final dew point moisture content offset; Indicates the basic dew point moisture content offset.

[0070] Dynamic gain function For a about The nonlinear function of When the preset threshold is exceeded, the function value will be significantly greater than 1, thereby amplifying the adjustment range and response speed of the supply air temperature and dew point humidity, and achieving proactive suppression of sudden or rapidly changing total heat loads.

[0071] Step S440 : generating control instructions for the supply air temperature, supply air volume, and humidity of the HVAC system for feedforward regulation based on the supply air temperature offset, dew point humidity offset, and the real-time status of the HVAC system.

[0072] In this step, the calculated supply air temperature and dew point offsets are combined with the HVAC system's real-time operating status to generate final control commands for supply air temperature, air volume, and humidity. By comprehensively considering the system's current state and predictive load adjustments, these generated control commands enable a rapid and precise response to indoor thermal and humidity demands through feedforward regulation, achieving a dynamic balance between temperature and humidity, improving system efficiency, and ensuring thermal comfort for occupants during various activities.

[0073] In one embodiment, the final formula is expressed as: ; ; in, Indicates the final supply air temperature; Indicates the basic supply air temperature; Indicates the final supply air temperature offset; Indicates the final dew point moisture content; Indicates basic dew point moisture content; Indicates the final dew point moisture content offset.

[0074] In one embodiment, the HVAC control method further includes the following steps: Step S500 : detecting indoor environment deviation caused by unpredictable disturbance or model error, and generating feedback correction instructions based on the detection result.

[0075] This step monitors deviations in indoor environmental parameters in real time to identify environmental changes caused by unpredictable disturbances (such as sudden increases or decreases in occupancy, door or window openings, equipment heating, etc.) or model errors. This step not only quantifies the difference between actual indoor temperature and humidity and predicted values ​​but also converts this deviation into a feedback correction signal, providing a reliable basis for subsequent control. By promptly detecting and quantifying these unforeseen disturbances, the system effectively avoids the delays or deviations associated with relying solely on feedforward predictions, thereby ensuring a comfortable and stable indoor environment.

[0076] Step S600 : combining the feedback correction instruction and the air supply temperature, air supply volume and humidity control instructions of the HVAC system for feedforward regulation to generate a final HVAC system regulation instruction.

[0077] In this step, the feedback correction instructions are combined with the feedforward adjustment instructions to generate the final HVAC system adjustment instructions. This step (S600) combines forward-looking prediction with real-time correction to achieve a proactive and responsive control strategy. Feedforward adjustment ensures proactive response to impending heat load changes, while feedback correction ensures timely compensation for unpredictable disturbances. The resulting adjustment instructions accurately control the supply air temperature, volume, and humidity while maintaining thermal comfort and air quality in the indoor environment, achieving efficient and dynamically responsive HVAC control.

[0078] According to the above embodiment, by decoupling the heat load to obtain the latent heat load and the sensible heat load, the basic control set points of the supply air temperature and humidity are determined respectively, and the dynamic gain function is introduced by using the total heat load change rate for correction, thereby forming a forward-looking supply air temperature offset and dew point moisture content offset. In addition, the present invention forms the final HVAC adjustment instruction by combining the feedforward control instruction based on prediction with the feedback correction instruction generated by the real-time detected environmental deviation, thereby achieving the coordinated work of the rapid response of the feedforward adjustment and the fine compensation of the feedback correction. The method of the present invention can not only respond to the sudden changes in the number of indoor people and activity intensity in advance, suppress the adjustment lag of environmental parameters, but also avoid energy waste caused by excessive or insufficient adjustment, while significantly improving the indoor thermal comfort, maintaining the efficiency and stability of the HVAC system operation.

[0079] In order to facilitate a more intuitive understanding of the above content of the present invention, a detailed description is given below in conjunction with a specific embodiment.

[0080] The implementation space is set as a modern smart gym with a total construction area of ​​500m 2 In this example, the aerobic training area is selected as the specific analysis object. The building parameters of this area are as follows: area 500m 2 The floor height is 4 meters. The air conditioning system uses an adjustable constant air volume system. The chilled water valve, supply air temperature, fresh air valve, and reheat capacity are all adjustable. The initial environmental conditions in the area are: dry-bulb temperature 26.0°C, relative humidity 60%, average wind speed 0.2m / s, base supply air temperature 18.0°C, and fresh air valve opening 30%.

[0081] The user situations are as follows: User A, female, 28 years old, weight 60kg, height 1.68m, resting heart rate 70bpm; User B, male, 40 years old, weight 85kg, height 1.80m, resting heart rate 75bpm. In the simulated training scenario, User A performed high-intensity training on the treadmill with a real-time heart rate of 150bpm; User B performed moderate-intensity training on the elliptical machine with a real-time heart rate of 125bpm. The data collected by the indoor air quality sensor showed that the regional temperature was 26.0℃ and the relative humidity was 60%. The Bluetooth beacon positioning system confirmed that both users were within 500m 2 In the aerobic training area.

[0082] For user A, the comfort benchmark is set as: =22℃; =50%. The weighting factor is: temperature =0.02; humidity =0.005.

[0083] .

[0084] According to the acceleration sensor data, after feature extraction and machine learning classification, the final activity label is output as "fast running". The actual activity metabolic rate benchmark table is obtained. At this time =8; =75%. Based on the user's age, their maximum heart rate is calculated to be 192 bpm.

[0085] .

[0086] The final individual metabolic rate is calculated as: .

[0087] For user B, the comfort benchmark is set as: =22℃; =50%. The weighting factor is: temperature =0.02; humidity =0.005.

[0088] .

[0089] According to the user's self-selected activity type, the final activity label is output as "elliptical machine", and the actual activity metabolic rate benchmark table is obtained. =5; =55%. Based on the user's age, their maximum heart rate is calculated to be 180 bpm.

[0090] .

[0091] The final individual metabolic rate is calculated as: .

[0092] The system identifies each person in the area through real-time positioning and sums up their respective metabolic equivalents. This process quantifies the total human heat source intensity in the area by converting real-time physiological metabolic equivalents into individual metabolic heat production rate in W.

[0093] After substituting the above formula, the body surface area of ​​user A is 1.69m 2 , user B’s body surface area is 2.05m 2 . Then for user A: =791.1W; for user B: =600.8W.

[0094] The total heat generation rate in the polymerization area is calculated as: .

[0095] Assuming the regional heat production rate change rate When the heat generation rate in the previous cycle is 100W / s, the system needs to perform a proactive response.

[0096] At this time, the total heat dissipation generated by the human body is defined as: .

[0097] Calculate the human body surface area according to the previous article and sum it up: .

[0098] Next, based on the evaporation characteristics between the human skin surface and the environment, the water vapor partial pressure on the skin surface and the current ambient air water vapor partial pressure are queried. Assuming the skin temperature is 35°C, the corresponding water vapor partial pressure on the skin surface is The regional ambient air temperature is 24°C and the relative humidity is 60%. The corresponding air water vapor partial pressure can be calculated as .

[0099] .

[0100] Based on the understanding of the body surface heat dissipation capacity and environmental conditions, the evaporative heat dissipation required by the human body in this area is calculated as: .

[0101] Assuming the latent heat of respiration is 20% of the total metabolism: .

[0102] For ease of calculation, let's assume that before a user begins high-intensity exercise, the air conditioning system is operating in a steady state, maintaining an indoor temperature of 24°C and 60% relative humidity. Assume the base supply air temperature is 20°C. At time t, the control strategy module receives the predicted data and allocates the predicted sensible and latent heat loads to different control paths.

[0103] Assume that the air supply volume of the air conditioning system in this area is 800m 3 / h, wind speed is 0.22m / s, then: .

[0104] Calculate the required moisture difference: .

[0105] Assuming the change rate of regional total metabolic heat production When the heat generation rate in the previous cycle is 100W / s, the system needs to respond proactively. The system detects that the change rate has triggered the strong response threshold and uses the built-in dynamic gain function to , to perform overshoot control on such drastic changes.

[0106] After calculation, it is assumed that the dynamic gain value of temperature at this time is , the dynamic gain with humidity is .

[0107] .

[0108] .

[0109] At this time, the calculated moisture content of the surface cooler section is: .

[0110] Set the machine's dew point relative humidity to 95%, and query the psychrometric chart to obtain a dew point temperature of 13.8°C.

[0111] At this time, the target supply air temperature is calculated as: .

[0112] At this time, the reheating section needs to be reheated to 4.55℃.

[0113] The above generated = 13.8℃ and = 18.35℃ as the main control instruction and immediately sent it to the building automation system for execution. At the same time, a standard feedback controller continuously monitors the actual indoor temperature and humidity. Assuming that due to the influence of solar radiation from the windows that is not covered by the model, the indoor temperature still has a deviation of +0.1℃ after executing the feedforward instruction, the PID controller will generate a correction value Finally, the system sends the set temperature to the reheat coil. , = 13.8℃.

[0114] The embodiment of the present invention also provides a HVAC control system based on dynamic heat load prediction, such as Figure 6 As shown, the HVAC control system includes a data acquisition module 101, a human metabolic rate calculation module 102, a load prediction module 103 and a control module 104. The data acquisition module 101 is used to obtain individual physiological data, environmental parameters and regional personnel distribution data in real time. The human metabolic rate calculation module 102 is used to determine the real-time individual metabolic rate equivalent based on the individual physiological data and environmental parameters. The load prediction module 103 is used to aggregate the individual metabolic rate equivalent according to the regional personnel distribution data, determine the total heat load and the total heat load change rate of each area in the room, and decompose the total heat load into sensible heat load and latent heat load. The control module 104 is used to generate the supply air temperature, supply air volume and humidity control instructions for the HVAC system for feedforward regulation based on the sensible heat load, latent heat load and the total heat load change rate.

[0115] An embodiment of the present invention also provides a HVAC control device based on dynamic heat load prediction, including: a processor 201, a memory 202, and a computer program stored in the memory 202 and configured to be executed by the processor 201. When the processor 201 executes the computer program, it implements the HVAC control method as described in any of the above embodiments.

[0116] When the processor 201 executes the computer program, the steps in the above HVAC control method embodiment are implemented, for example Figure 1 Alternatively, when the processor 201 executes the computer program, the functions of each module / unit in the above HVAC control system are realized, such as Figure 6 The functions of each module of the HVAC control system are shown.

[0117] For example, the computer program can be divided into one or more modules, one or more of which are stored in the memory 202 and executed by the processor 201 to implement the present invention. One or more modules can be a series of computer program instruction segments that can perform specific functions. These instruction segments are used to describe the execution process of the computer program in the HVAC control system.

[0118] The processor 201 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Processor 201 is the control center of the HVAC control system, connecting various components of the entire HVAC control system using various interfaces and lines.

[0119] Memory 202 can be used to store computer programs and / or modules. Processor 201 implements various functions of the HVAC control system by running or executing the computer programs and / or modules stored in memory 202 and accessing data stored in memory 202. Memory 202 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function, while the data storage area may store data generated based on the use of the HVAC control system. Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0120] If the modules / units of the HVAC control system are implemented as software functional units and sold or used as standalone products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include any entity or device capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media.

[0121] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0122] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A HVAC control method based on dynamic heat load prediction, characterized in that: The following steps are involved: Real-time acquisition of indoor individual physiological data, environmental parameters, and regional personnel distribution data; Determining a real-time individual metabolic rate equivalent based on the individual physiological data and environmental parameters; Aggregating the individual metabolic rate equivalents according to the regional personnel distribution data, determining the total heat load and the total heat load change rate of each indoor area, and decomposing the total heat load into sensible heat load and latent heat load; Based on the sensible heat load, latent heat load and the total heat load change rate, supply air temperature, supply air volume and humidity control instructions for the HVAC system for feedforward regulation are generated.

2. The HVAC control method according to claim 1, wherein: The specific steps of determining the real-time individual metabolic rate equivalent based on the individual physiological data and environmental parameters include: Based on the environmental parameters, evaluating the impact of the indoor environment on the individual metabolic rate to obtain an environmental correction factor; Identify individual exercise types and determine corresponding baseline metabolic equivalents and real-time baseline heart rate values ​​based on the exercise types; Determining individual exercise intensity based on the real-time baseline heart rate value and the corresponding baseline heart rate interval; The real-time individual metabolic rate equivalent is calculated based on the environmental correction factor, the baseline metabolic equivalent and the individual exercise intensity.

3. The HVAC control method according to claim 2, wherein: The calculation formula of the individual metabolic rate equivalent is: ； in, is the metabolic rate of a single individual at an instant; is the environmental correction factor; is the individual exercise intensity; Indicates that the motion type is The individual heart rate baseline value is calculated when Indicates that the motion type is The actual benchmark value corresponding to the actual activity metabolic rate benchmark table.

4. The HVAC control method according to claim 2, wherein: The specific steps of identifying the individual's movement type include: Acquiring three-axis acceleration data of a wearable device worn by an individual, and performing feature extraction on the three-axis acceleration data; Inputting the extracted features into a pre-trained classification model to obtain motion type information based on the three-axis acceleration data; The individual selects the current activity type from a preset activity list through the software interface, and obtains the exercise type information based on the user's selection; The final individual motion type is determined by combining the motion type information based on the three-axis acceleration data and the motion type information based on the user's selection.

5. The HVAC control method according to claim 2, wherein: The specific steps of aggregating the individual metabolic rate equivalents according to the regional personnel distribution data, determining the total heat load and the total heat load change rate of each indoor area, and decomposing the total heat load into sensible heat load and latent heat load include: Based on the regional personnel distribution data, the individual metabolic rate equivalents of each person in the same area are aggregated to obtain the total heat load of each indoor area; Calculating the rate of change of the total heat load of each indoor area over time to obtain the total heat load change rate, so as to quantify the change direction and speed of the total heat load; calculating the evaporative heat dissipation required by the human body and the maximum evaporative heat dissipation capacity of the region based on the total heat load and environmental parameters, and comparing the evaporative heat dissipation required by the human body with the maximum evaporative heat dissipation capacity of the region to obtain a final latent heat load; The sensible heat load of each zone is obtained by subtracting the latent heat load from the total heat load.

6. The HVAC control method according to claim 5, characterized in that: The specific steps of generating the supply air temperature, supply air volume and humidity control instructions for the HVAC system for feedforward regulation based on the sensible heat load, latent heat load and the total heat load change rate include: Determining a base supply air temperature offset based on the sensible heat load and the current supply air temperature of the HVAC system; Determining a basic dew point humidity offset based on the latent heat load and the current air supply volume of the HVAC system; Based on the total heat load change rate, the basic supply air temperature offset and the basic dew point humidity offset are corrected by a dynamic gain function to obtain a final supply air temperature offset and a final dew point humidity offset; Combining the supply air temperature offset, the dew point moisture offset and the real-time status of the HVAC system, a supply air temperature, supply air volume and humidity control instruction for the HVAC system for feedforward regulation is generated.

7. The HVAC control method according to claim 6, wherein: The HVAC control method further includes: Detect indoor environment deviations caused by unpredictable disturbances or model errors, and generate feedback correction instructions based on the detection results; The feedback correction instruction and the air supply temperature, air supply volume and humidity control instruction of the HVAC system for feedforward regulation are combined to generate a final HVAC system regulation instruction.

8. A HVAC control system based on dynamic heat load prediction, characterized in that: include: Data acquisition module, used to obtain indoor individual physiological data, environmental parameters and regional personnel distribution data in real time; A human metabolic rate calculation module, configured to determine a real-time individual metabolic rate equivalent based on the individual physiological data and environmental parameters; a load prediction module for aggregating the individual metabolic rate equivalents based on the regional personnel distribution data, determining the total heat load and the rate of change of the total heat load for each indoor area, and decomposing the total heat load into sensible heat load and latent heat load; The control module is used to generate air supply temperature, air supply volume and humidity control instructions for the HVAC system for feedforward regulation based on the sensible heat load, latent heat load and the total heat load change rate.

9. A device, characterized in that include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the HVAC control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the HVAC control method according to any one of claims 1 to 7 are implemented.

Images