An air conditioning system dynamic control system and method based on human behavior

Abstract

The application relates to the technical field of air conditioner control, in particular to an air conditioner system dynamic control system and method based on personnel behavior. The system comprises a data acquisition module, which is used for acquiring personnel data and environment data from a perception module; a static analysis module, which is used for generating the static load of a collection space according to the environment data of the collection space; a dynamic perception module, which is used for analyzing the number of personnel, the behavior of personnel and the behavior of facilities in the collection space according to the personnel data and the environment data in the collection space in real time, generating the dynamic load of the collection space according to the number of personnel, the behavior of personnel and the behavior of facilities, and generating the supply demand of the collection space according to the dynamic load; an adjustment control module, which is used for controlling the air conditioner to start when the static load reaches an air conditioner starting threshold, and generating the supply demand of the collection space according to the dynamic load; and a device driving module, which is used for determining the refrigerating capacity or the heating capacity and the air supply capacity of the air conditioner host to each space according to the current supply demand of each space and generating an adjustment instruction.

Description

Technical Field

[0001] This invention relates to the field of air conditioning control technology, and specifically to a dynamic control system and method for air conditioning systems based on human behavior. Background Technology

[0002] Traditional air conditioning control methods typically operate based on fixed temperature setpoints and preset operating models. However, due to varying activity levels, time periods, and spatial distributions, people's comfort requirements for the indoor environment differ. The comfortable temperature and humidity range for individuals varies with individual differences, seasonal changes, activity levels, and clothing levels. This dynamic nature of thermal comfort makes it difficult for people to accurately determine the temperature that makes them feel comfortable. Furthermore, temperature setpoint-based thermal environment control methods can easily lead to excessively cold or hot rooms and energy waste. For example, when people are densely populated, their requirements for indoor temperature and ventilation differ from when people are sparsely populated or stationary. Continuing to maintain high-energy-consuming air conditioning operation when people are away from the room for extended periods results in energy waste. Therefore, traditional parameter setpoint-based control methods are not well-suited for meeting the comfort requirements of indoor air conditioning thermal environment control.

[0003] In order to provide reference and suggestions for achieving comfortable, healthy and energy-saving indoor thermal environment control and regulation, it is necessary to propose a dynamic control system and method for air conditioning systems based on human behavior, so as to improve the comfort and energy efficiency of air conditioning systems. Summary of the Invention

[0004] The technical problem solved by this invention is to provide a dynamic control system for an air conditioning system based on human behavior. By dynamically adjusting the operating parameters of the air conditioning system according to the actual behavior and activities of people, the system avoids idling and excessive cooling / heating when no one is present, and can effectively reduce the energy consumption of the air conditioning system.

[0005] The basic solution provided by this invention is: a dynamic control system for an air conditioning system based on human behavior, including a server, a sensing module, and an air conditioning drive module. The sensing module includes a human sensing module and an environmental sensing module. The human sensing module is used to collect human data in the space, and the environmental sensing module is used to collect environmental data in the space. The server includes a data acquisition module, a static analysis module, a dynamic sensing module, an adjustment and control module, and an equipment drive module. The data acquisition module is used to acquire personnel data and environmental data from the sensing module. The static analysis module is used to generate the static load of the acquisition space based on the environmental data of the acquisition space. The dynamic sensing module is used to analyze the number of people, their behavior, and the behavior of facilities in the data collection space in real time based on the personnel data and environmental data in the data collection space, and to generate the dynamic load of the data collection space based on the number of people, their behavior, and the behavior of facilities. The adjustment and control module is used to control the air conditioner to turn on when the static load reaches the air conditioner start threshold, and to generate the supply demand of the collected space based on the dynamic load. The device driver module is used to determine the cooling or heating capacity and air volume of the air conditioning unit for each space based on the current supply demand of each space, and generate adjustment instructions, which are then sent to the air conditioning driver module. The device driver module is also used to generate adjustment instructions based on the fine-tuning amount.

[0006] The principle and advantages of this invention are as follows: by integrating a server, a sensing module, and an air conditioning drive module, intelligent and adaptive control of the air conditioning system is achieved. The sensing module is divided into a personnel sensing module and an environmental sensing module, which are responsible for collecting personnel data and environmental data within the space, respectively. The server includes a data acquisition module, a static analysis module, a dynamic sensing module, an adjustment and control module, and an equipment drive module. The data acquisition module obtains real-time data from the sensing module; the static analysis module calculates the static load based on the environmental data, reflecting the heat load of the building structure itself; the dynamic sensing module analyzes the number of people, personnel behavior, and facility behavior in real time to generate a dynamic load, which represents the variable heat load generated by personnel activities and equipment use; the adjustment and control module controls the air conditioning to start when the static load reaches a preset air conditioning start threshold, and generates supply and demand based on the dynamic load to ensure that the air conditioning output matches the actual demand; the equipment drive module determines the cooling capacity, heating capacity, and air volume of the air conditioning unit for each space based on the supply and demand, and generates adjustment commands to send to the air conditioning drive module. At the same time, the equipment drive module can also make fine adjustments based on the fine-tuning amount.

[0007] Compared to existing technologies, this invention overcomes the limitations of traditional air conditioning control based on fixed temperature setpoints. Traditional methods cannot adapt to heat load fluctuations caused by changes in human behavior, easily leading to energy waste and decreased comfort. This invention achieves real-time response and precise control of the air conditioning system through a combination of static and dynamic load analysis. For example, when there is a high density of people or intense activity, the system automatically increases cooling capacity to offset the additional heat load; when people leave or activity decreases, the system reduces output to avoid unnecessary energy consumption. This not only significantly improves indoor comfort, keeping users within a suitable temperature range, but also greatly improves energy efficiency and reduces the operating costs of the air conditioning system. Furthermore, the system reduces human intervention through automated adjustment, enhancing the user experience. It is suitable for various scenarios such as offices and residences, promoting smart buildings and sustainable development.

[0008] Furthermore, the environmental sensing module includes an indoor sensing module and an outdoor sensing module, and the static analysis module includes a structure management module; the indoor sensing module is used to acquire the indoor temperature within the acquisition space, and the outdoor sensing module is used to acquire the outdoor temperature. The structure management module pre-stores the enclosure structure data of each acquisition space, including the heat transfer coefficient and area of ​​the enclosure structure of the acquisition space. The static analysis module is used to obtain the indoor and outdoor temperature difference based on the indoor and outdoor temperatures, and to obtain the static load of the acquisition space by combining the data of the building envelope.

[0009] in, This represents the heat transfer coefficient of the building envelope. Indicates the area of ​​the enclosure structure. This indicates the temperature difference between indoors and outdoors.

[0010] Air conditioning start-up control is optimized by more accurately calculating static load. The environmental sensing module includes an indoor sensing module and an outdoor sensing module, used to collect indoor and outdoor temperatures, respectively; the static analysis module includes a structural management module, which pre-stores the building envelope data for each collected space, such as heat transfer coefficients and area. Based on the indoor-outdoor temperature difference and the building envelope data, the static analysis module uses a formula to calculate the static load, taking into account the heat conduction characteristics of the building envelope, thus more accurately reflecting the heat load caused by the indoor-outdoor temperature difference.

[0011] This invention addresses the problem of traditional air conditioning systems neglecting the influence of building structures. Traditional systems often rely solely on simple temperature thresholds for control, leading to inaccurate load estimation and energy waste. By introducing building envelope parameters, this invention makes static load calculation more scientific and reliable, ensuring that air conditioning only starts when necessary and avoiding malfunctions caused by ambient temperature fluctuations. For example, in spaces with good building insulation, the static load may be lower, and the system will delay air conditioning startup to save energy; conversely, in spaces with poor insulation, the system will respond promptly to prevent temperature imbalances. This precise calculation not only improves the energy efficiency of the air conditioning system but also extends equipment lifespan and reduces wear and tear from frequent start-stop cycles. Simultaneously, it provides a solid foundation for dynamic load adjustment, making the overall control system more stable and efficient. It is particularly suitable for complex building environments, such as large office buildings or commercial centers, where differences in building envelopes significantly impact thermal management.

[0012] Furthermore, the dynamic sensing module includes a personnel sensing module, an equipment sensing module, a lighting sensing module, and other sensing modules; The personnel sensing module is used to identify the activity intensity of personnel in the acquisition space based on the images of personnel in the acquisition space, and to identify the heat dissipation of personnel based on the number of personnel and the activity intensity of personnel. The device sensing module is used to identify the heat dissipation of devices in the data acquisition space based on the device type and the on / off status of each device. The lighting sensing module is used to identify the amount of heat dissipation from lighting devices in the data collection space based on the activation status of these devices. Other sensing modules are used to identify one or more of the air infiltration heat and solar radiation fluctuations in the collection space to obtain other dynamic loads; The dynamic sensing module is used to obtain the dynamic load based on the heat dissipation of personnel, equipment, lighting, and other dynamic loads.

[0013] This represents the total dynamic load at time t. This represents the amount of heat dissipated by the personnel at time t. This represents the amount of heat dissipated by the device at time t. This represents the amount of heat dissipated by the lighting at time t. This represents the other heat dissipation at time t.

[0014] The principle is to capture the dynamic changes of indoor heat sources through multi-source sensing and real-time calculation, thereby generating accurate dynamic load values. The dynamic sensing module includes a personnel sensing module, an equipment sensing module, a lighting sensing module, and other sensing modules. The personnel sensing module analyzes personnel images to identify the intensity of personnel activity and calculates personnel heat dissipation based on the number of people; the equipment sensing module identifies equipment heat dissipation based on equipment type and on / off status; the lighting sensing module calculates lighting heat dissipation based on the on / off status of lighting equipment; and other sensing modules are responsible for identifying additional factors such as air infiltration heat and solar radiation fluctuations to obtain other dynamic loads. All these heat dissipations are aggregated in the dynamic sensing module, and the total dynamic load value is calculated using a formula that reflects the characteristics of heat load changes over time.

[0015] This invention comprehensively covers the impact of indoor heat sources. Traditional air conditioning systems often fail to respond in real time to changes in occupant behavior, equipment operation, and lighting, leading to control lag and decreased comfort. By integrating multiple sensing technologies, this invention achieves real-time monitoring and adjustment of dynamic factors. For example, when people gather in a meeting room or equipment is used extensively, the system rapidly increases cooling capacity; when lights are turned off or people leave, the system reduces output to avoid energy waste. This dynamic response not only improves the stability and comfort of the indoor environment but also significantly optimizes energy use and reduces carbon emissions. Furthermore, it supports personalized control, allocating resources according to the heat load requirements of different areas, improving system flexibility and reliability, making it suitable for dynamic environments such as schools and hospitals.

[0016] Furthermore, the personnel perception module also includes a clothing thermal resistance recognition module, used to identify the clothing outline of personnel based on personnel images within the acquisition space, and to identify the real-time clothing thermal resistance coefficient of each personnel by the coverage and volume of the clothing outline relative to a standard human body model. This is achieved by identifying and defining each independent human body region from the personnel images, and performing visual feature analysis on each human body region. By analyzing the differences between pixels within the human body region and a preset skin color model, the area of ​​the body surface covered by clothing is identified, and the proportion of this area to the total area of ​​the human body region is calculated to obtain the body region coverage rate. By comparing the actual outer contour of the human body region with the contour of the benchmark human body model generated based on the human body posture, the contour deviation between the two in key torso and limb parts is measured to obtain the fabric contour fluffiness. By identifying pixels in the human body region that conform to preset skin color and texture characteristics, the proportion of exposed skin area to the total area is calculated to obtain the percentage of exposed skin area; The dynamic sensing module is used to correct the heat dissipation of personnel based on the real-time thermal resistance coefficient of clothing.

[0017] in This represents the corrected total heat dissipation from personnel, where n is the number of personnel. This is the basic unit heat dissipation calculated based on the activity intensity of the j-th person. This is the preset thermal resistance influence coefficient. Let be the thermal resistance coefficient of the clothing worn by the j-th person at time t; The adjustment and control module also includes a clothing change response module, which is used to monitor the rate of change of the average thermal resistance coefficient of clothing of people in the acquisition space. When the rate of change is lower than the preset negative threshold within the preset time window, it is determined that a collective clothing reduction event has occurred. When a collective clothing reduction event occurs, a phased heating command is generated. The phased heating command includes a temporary target temperature higher than the current set value and a transition time. The device drive module gradually adjusts the current set value to the temporary target temperature within the transition time according to the phased temperature increase command.

[0018] Traditional air conditioning systems typically consider only two factors when calculating the heat load generated by people: the number of people in the room and the extent of their activity. For example, the heat dissipation calculated by the system will differ between ten people sitting in a meeting and ten people doing exercises. However, this traditional method overlooks a crucial everyday fact: the thickness of clothing people wear significantly affects their heat dissipation. In winter, a person wearing a thick down jacket sitting indoors has difficulty dissipating body heat; when they remove their coat and wear only a sweater, the rate of heat dissipation increases dramatically. If the air conditioning system only knows that the number of people in the room and their activity levels haven't changed, it will continue to supply cold air based on the original heat calculations. This will result in those who have removed their coats feeling chilly, while those who haven't yet removed their clothes may still feel stuffy. To address this issue, this solution adds intelligent recognition of people's clothing status to the existing perception system. The system analyzes human images through cameras, not for facial recognition, but for analyzing the outline coverage and relative thickness of clothing, thereby estimating a coefficient representing the warmth of the clothing, which we call the clothing thermal resistance coefficient. This coefficient is incorporated into the core heat load calculation formula. Simply put, the system determines that the more layers a person wears, the less heat they actually dissipate into the room, thus reducing the heat contribution value during calculation. More importantly, the system can detect changes in collective behavior. For example, in a meeting room at the beginning of the morning, everyone has just entered from outside, the air conditioning has just been turned on, and everyone is wearing coats. Then, within half an hour, most people gradually remove their coats. Once the system recognizes this trend of lighter clothing, it interprets it as a key event: people now need a warmer environment to compensate for the increased heat dissipation due to reduced clothing. Therefore, it instructs the air conditioning system to gradually increase the target room temperature by one or two degrees over a period of time and control the airflow to become gentler, allowing the temperature to smoothly transition to a more comfortable state, rather than continuing to blow excessively cold air.

[0019] Existing technologies utilize multiple sensors to more accurately count people and even differentiate room types. However, their core calculation of personnel load remains at the stage of multiplying the number of people by a fixed coefficient, or combining it with other heat sources such as equipment and lighting. They fail to perceive or respond to the crucial factor of dynamic changes in clothing. Therefore, during seasonal transitions in autumn / winter or spring / summer, in places with frequent personnel movement and significant clothing changes, such as offices, schools, and shopping mall entrances, existing systems experience significant control failures, leading to energy waste and decreased comfort. This solution, however, introduces a clothing thermal resistance recognition and event response mechanism, incorporating the individual's own, real-time changing thermal resistance attributes into the automatic control logic. This deepens the air conditioning system's perception of people from a vague group count to the individual state level directly related to thermal balance. The primary advantage is a significant improvement in thermal comfort in specific scenarios, directly addressing the practical pain points of feeling cold after removing clothing and hot while putting it on. Secondly, because the calculation of personnel heat dissipation is more accurate, the system's supply of cooling or heating is more closely aligned with actual needs, avoiding overcooling or overheating.

[0020] Furthermore, the server also includes a load trend prediction module, which includes a load identification module and a load prediction module; The load identification module is used to calculate the load at each moment according to the preset time interval, and to calculate the load change at each time interval; The load forecasting module is used to predict future load changes and obtain load demand based on historical data, current personnel data, environmental data, and various load changes. The regulation and control module is also used to generate supply and demand at corresponding times based on future load changes.

[0021] By using historical data and real-time analysis to predict future load changes, the air conditioning system achieves proactive control. The load trend prediction module includes a load identification module and a load prediction module: the load identification module calculates various loads at each moment according to preset time intervals and analyzes load change trends; the load prediction module combines historical data, current personnel data, environmental data, and load changes, using statistical or machine learning methods to predict future load demand. Based on these prediction results, the regulation and control module generates supply and demand at the corresponding time, enabling the air conditioning system to adjust its operating status in advance.

[0022] Overcoming the latency issues of traditional reactive control, which operates solely based on current conditions, often leads to energy spikes and equipment wear, this invention achieves smooth energy management and a more stable indoor environment by predicting load trends. For example, when it predicts a surge of people entering a space, the system can increase cooling capacity in advance to prevent a sudden temperature rise; when it predicts a decrease in load, the system can reduce output in advance to save energy. This predictive control not only improves energy efficiency and reduces operating costs but also extends the lifespan of air conditioning equipment and avoids frequent start-ups and shutdowns. Simultaneously, it enhances the system's adaptability, resulting in a more seamless and comfortable user experience, making it particularly suitable for locations with strong time-regularities, such as offices or schools, where load changes are highly predictable.

[0023] Furthermore, the personnel sensing module collects personnel images through a camera, and obtains the posture, movement and number of people in the collection space by recognizing the personnel images. It uses a Wi-Fi probe to determine the entry and exit of personnel, and uses a pressure sensor installed on the seat to sense whether the personnel are in their seats.

[0024] This invention also discloses a dynamic control method for an air conditioning system based on human behavior, comprising the following steps: S1. Acquire personnel data and environmental data within the data collection area; S2. Generate the static load of the acquisition space based on the environmental data of the acquisition space; S3. Analyze the number of people, their behavior, and the behavior of facilities in the data collection space in real time based on the personnel data and environmental data in the data collection space, and generate the dynamic load of the data collection space based on the number of people, their behavior, and the behavior of facilities. S4. When the static load reaches the air conditioner start-up threshold, control the air conditioner to turn on and generate the supply demand of the collection space based on the dynamic load. S5. Based on the current supply demand of each space, determine the cooling or heating capacity and air volume of the air conditioning unit for each space and generate adjustment instructions, which are then sent to the air conditioning drive module. The equipment drive module is also used to generate adjustment instructions based on the fine-tuning amount.

[0025] Furthermore, S2 includes the following steps: S21. Pre-store the enclosure structure data of each acquisition space, wherein the enclosure structure data includes the heat transfer coefficient and area of ​​the enclosure structure of the acquisition space. S22. Based on the indoor and outdoor temperatures, obtain the indoor-outdoor temperature difference, and combine this with the data from the building envelope to obtain the static load of the space being surveyed.

[0026] in, This represents the heat transfer coefficient of the building envelope. Indicates the area of ​​the enclosure structure. This indicates the temperature difference between indoors and outdoors.

[0027] Furthermore, S3 includes the following steps: S31. Based on the images of people in the acquisition space, identify the activity intensity of the people in the acquisition space, and based on the number of people and the activity intensity of the people, identify the heat dissipation of the people. S32. Identify the heat dissipation of the devices in the acquisition space based on the device type and the on / off status of each device. S33. Identify the heat dissipation of the lighting in the acquisition space based on the activation device of the lighting equipment in the acquisition space; S34. Identify one or more of the air infiltration heat and solar radiation fluctuations in the acquisition space to obtain other dynamic loads; S35. Based on the heat dissipation from personnel, equipment, lighting, and other dynamic loads, the dynamic load is obtained:

[0028] This represents the total dynamic load at time t. This represents the amount of heat dissipated by the personnel at time t. This represents the amount of heat dissipated by the device at time t. This represents the amount of heat dissipated by the lighting at time t. This represents the other heat dissipation at time t.

[0029] Furthermore, it also includes the following steps: S61. Calculate the load at each moment according to the preset time interval, and calculate the load change at each time interval; S62. Based on historical data, current personnel data, environmental data, and various load changes, predict future load changes to obtain load demand; S63. Based on the load changes at future times, generate supply and demand at the corresponding times. Attached Figure Description

[0030] Figure 1 This is a logic block diagram of an embodiment of a dynamic control system for an air conditioning system based on human behavior according to the present invention. Detailed Implementation

[0031] The following detailed description illustrates the specific implementation method: The basic implementation examples are as follows: Figure 1 As shown: A dynamic control system for an air conditioning system based on human behavior includes a server, a sensing module, and an air conditioning drive module. The sensing module includes a human sensing module and an environmental sensing module. The human sensing module is used to collect human data in the space, and the environmental sensing module is used to collect environmental data in the space. The server includes a data acquisition module, a static analysis module, a dynamic sensing module, an adjustment and control module, and an equipment drive module. The data acquisition module is used to acquire personnel data and environmental data from the sensing module. The static analysis module is used to generate the static load of the acquisition space based on the environmental data of the acquisition space. The dynamic sensing module is used to analyze the number of people, their behavior, and the behavior of facilities in the data collection space in real time based on the personnel data and environmental data in the data collection space, and to generate the dynamic load of the data collection space based on the number of people, their behavior, and the behavior of facilities. The adjustment and control module is used to control the air conditioner to turn on when the static load reaches the air conditioner start threshold, and to generate the supply demand of the collected space based on the dynamic load. The device driver module is used to determine the cooling or heating capacity and air volume of the air conditioning unit for each space based on the current supply demand of each space, and generate adjustment instructions, which are then sent to the air conditioning driver module. The device driver module is also used to generate adjustment instructions based on the fine-tuning amount.

[0032] By integrating a server, sensing modules, and air conditioning drive modules, intelligent and adaptive control of the air conditioning system is achieved. The sensing modules are divided into personnel sensing modules and environmental sensing modules, responsible for collecting personnel data and environmental data within the space, respectively. The server includes a data acquisition module, a static analysis module, a dynamic sensing module, a regulation and control module, and an equipment drive module. The data acquisition module obtains real-time data from the sensing modules; the static analysis module calculates the static load based on environmental data, reflecting the heat load of the building structure itself; the dynamic sensing module analyzes the number of people, their behavior, and facility behavior in real time to generate a dynamic load, which represents the variable heat load generated by personnel activity and equipment use; the regulation and control module controls the air conditioning to start when the static load reaches a preset air conditioning start-up threshold and generates supply and demand based on the dynamic load to ensure that the air conditioning output matches the actual demand; the equipment drive module determines the cooling capacity, heating capacity, and air volume of the air conditioning unit for each space based on the supply and demand, generates adjustment commands and sends them to the air conditioning drive module, which can also make fine adjustments based on the fine-tuning amount.

[0033] Compared to existing technologies, this invention overcomes the limitations of traditional air conditioning control based on fixed temperature setpoints. Traditional methods cannot adapt to heat load fluctuations caused by changes in human behavior, easily leading to energy waste and decreased comfort. This invention achieves real-time response and precise control of the air conditioning system through a combination of static and dynamic load analysis. For example, when there is a high density of people or intense activity, the system automatically increases cooling capacity to offset the additional heat load; when people leave or activity decreases, the system reduces output to avoid unnecessary energy consumption. This not only significantly improves indoor comfort, keeping users within a suitable temperature range, but also greatly improves energy efficiency and reduces the operating costs of the air conditioning system. Furthermore, the system reduces human intervention through automated adjustment, enhancing the user experience. It is suitable for various scenarios such as offices and residences, promoting smart buildings and sustainable development.

[0034] The environmental sensing module includes an indoor sensing module and an outdoor sensing module, and the static analysis module includes a structure management module; the indoor sensing module is used to acquire the indoor temperature in the acquisition space, and the outdoor sensing module is used to acquire the outdoor temperature. The structure management module pre-stores the enclosure structure data of each acquisition space, including the heat transfer coefficient and area of ​​the enclosure structure of the acquisition space. The static analysis module is used to obtain the indoor and outdoor temperature difference based on the indoor and outdoor temperatures, and to obtain the static load of the acquisition space by combining the data of the building envelope.

[0035] in, This represents the heat transfer coefficient of the building envelope. Indicates the area of ​​the enclosure structure. This indicates the temperature difference between indoors and outdoors.

[0036] Air conditioning start-up control is optimized by more accurately calculating static load. The environmental sensing module includes an indoor sensing module and an outdoor sensing module, used to collect indoor and outdoor temperatures, respectively; the static analysis module includes a structural management module, which pre-stores the building envelope data for each collected space, such as heat transfer coefficients and area. Based on the indoor-outdoor temperature difference and the building envelope data, the static analysis module uses a formula to calculate the static load, taking into account the heat conduction characteristics of the building envelope, thus more accurately reflecting the heat load caused by the indoor-outdoor temperature difference.

[0037] This invention addresses the problem of traditional air conditioning systems neglecting the influence of building structures. Traditional systems often rely solely on simple temperature thresholds for control, leading to inaccurate load estimation and energy waste. By introducing building envelope parameters, this invention makes static load calculation more scientific and reliable, ensuring that air conditioning only starts when necessary and avoiding malfunctions caused by ambient temperature fluctuations. For example, in spaces with good building insulation, the static load may be lower, and the system will delay air conditioning startup to save energy; conversely, in spaces with poor insulation, the system will respond promptly to prevent temperature imbalances. This precise calculation not only improves the energy efficiency of the air conditioning system but also extends equipment lifespan and reduces wear and tear from frequent start-stop cycles. Simultaneously, it provides a solid foundation for dynamic load adjustment, making the overall control system more stable and efficient. It is particularly suitable for complex building environments, such as large office buildings or commercial centers, where differences in building envelopes significantly impact thermal management.

[0038] The dynamic sensing module includes a personnel sensing module, an equipment sensing module, a lighting sensing module, and other sensing modules; The personnel sensing module is used to identify the activity intensity of personnel in the acquisition space based on the images of personnel in the acquisition space, and to identify the heat dissipation of personnel based on the number of personnel and the activity intensity of personnel. The device sensing module is used to identify the heat dissipation of devices in the data acquisition space based on the device type and the on / off status of each device. The lighting sensing module is used to identify the amount of heat dissipation from lighting devices in the data collection space based on the activation status of these devices. Other sensing modules are used to identify one or more of the air infiltration heat and solar radiation fluctuations in the collection space to obtain other dynamic loads; The dynamic sensing module is used to obtain the dynamic load based on the heat dissipation of personnel, equipment, lighting, and other dynamic loads.

[0039] This represents the total dynamic load at time t. This represents the amount of heat dissipated by the personnel at time t. This represents the amount of heat dissipated by the device at time t. This represents the amount of heat dissipated by the lighting at time t. This represents other heat dissipation at time t; The personnel perception module also includes a clothing thermal resistance recognition module, which is used to identify the clothing outline of personnel based on the personnel images in the acquisition space, and to identify the real-time clothing thermal resistance coefficient of each person by the coverage and volume of the clothing outline relative to a standard human body model. It also identifies and frames each independent human body region from the personnel images and performs visual feature analysis on each human body region. By analyzing the differences between pixels within the human body region and a preset skin color model, the area of ​​the body surface covered by clothing is identified, and the proportion of this area to the total area of ​​the human body region is calculated to obtain the body region coverage rate. By comparing the actual outer contour of the human body region with the contour of the benchmark human body model generated based on the human body posture, the contour deviation between the two in key torso and limb parts is measured to obtain the fabric contour fluffiness. By identifying pixels in the human body region that conform to preset skin color and texture characteristics, the proportion of exposed skin area to the total area is calculated to obtain the percentage of exposed skin area; The dynamic sensing module is used to correct the heat dissipation of personnel based on the real-time thermal resistance coefficient of clothing.

[0040] in This represents the corrected total heat dissipation from personnel, where n is the number of personnel. This is the basic unit heat dissipation calculated based on the activity intensity of the j-th person. This is the preset thermal resistance influence coefficient. Let be the thermal resistance coefficient of the clothing worn by the j-th person at time t; The adjustment and control module also includes a clothing change response module, which is used to monitor the rate of change of the average thermal resistance coefficient of clothing of people in the acquisition space. When the rate of change is lower than the preset negative threshold within the preset time window, it is determined that a collective clothing reduction event has occurred. When a collective clothing reduction event occurs, a phased heating command is generated. The phased heating command includes a temporary target temperature higher than the current set value and a transition time. The device drive module gradually adjusts the current set value to the temporary target temperature within the transition time according to the phased temperature increase command.

[0041] Traditional air conditioning systems typically consider only two factors when calculating the heat load generated by people: the number of people in the room and the extent of their activity. For example, the heat dissipation calculated by the system will differ between ten people sitting in a meeting and ten people doing exercises. However, this traditional method overlooks a crucial everyday fact: the thickness of clothing people wear significantly affects their heat dissipation. In winter, a person wearing a thick down jacket sitting indoors has difficulty dissipating body heat; when they remove their coat and wear only a sweater, the rate of heat dissipation increases dramatically. If the air conditioning system only knows that the number of people in the room and their activity levels haven't changed, it will continue to supply cold air based on the original heat calculations. This will result in those who have removed their coats feeling chilly, while those who haven't yet removed their clothes may still feel stuffy. To address this issue, this solution adds intelligent recognition of people's clothing status to the existing perception system. The system analyzes human images through cameras, not for facial recognition, but for analyzing the outline coverage and relative thickness of clothing, thereby estimating a coefficient representing the warmth of the clothing, which we call the clothing thermal resistance coefficient. This coefficient is incorporated into the core heat load calculation formula. Simply put, the system determines that the more layers a person wears, the less heat they actually dissipate into the room, thus reducing the heat contribution value during calculation. More importantly, the system can detect changes in collective behavior. For example, in a meeting room at the beginning of the morning, everyone has just entered from outside, the air conditioning has just been turned on, and everyone is wearing coats. Then, within half an hour, most people gradually remove their coats. Once the system recognizes this trend of lighter clothing, it interprets it as a key event: people now need a warmer environment to compensate for the increased heat dissipation due to reduced clothing. Therefore, it instructs the air conditioning system to gradually increase the target room temperature by one or two degrees over a period of time and control the airflow to become gentler, allowing the temperature to smoothly transition to a more comfortable state, rather than continuing to blow excessively cold air.

[0042] Existing technologies utilize multiple sensors to more accurately count people and even differentiate room types. However, their core calculation of personnel load remains at the stage of multiplying the number of people by a fixed coefficient, or combining it with other heat sources such as equipment and lighting. They fail to perceive or respond to the crucial factor of dynamic changes in clothing. Therefore, during seasonal transitions in autumn / winter or spring / summer, in places with frequent personnel movement and significant clothing changes, such as offices, schools, and shopping mall entrances, existing systems experience significant control failures, leading to energy waste and decreased comfort. This solution, however, introduces a clothing thermal resistance recognition and event response mechanism, incorporating the individual's own, real-time changing thermal resistance attributes into the automatic control logic. This deepens the air conditioning system's perception of people from a vague group count to the individual state level directly related to thermal balance. The primary advantage is a significant improvement in thermal comfort in specific scenarios, directly addressing the practical pain points of feeling cold after removing clothing and hot while putting it on. Secondly, because the calculation of personnel heat dissipation is more accurate, the system's supply of cooling or heating is more closely aligned with actual needs, avoiding overcooling or overheating.

[0043] The principle is to capture the dynamic changes of indoor heat sources through multi-source sensing and real-time calculation, thereby generating accurate dynamic load values. The dynamic sensing module includes a personnel sensing module, an equipment sensing module, a lighting sensing module, and other sensing modules. The personnel sensing module analyzes personnel images to identify the intensity of personnel activity and calculates personnel heat dissipation based on the number of people; the equipment sensing module identifies equipment heat dissipation based on equipment type and on / off status; the lighting sensing module calculates lighting heat dissipation based on the on / off status of lighting equipment; and other sensing modules are responsible for identifying additional factors such as air infiltration heat and solar radiation fluctuations to obtain other dynamic loads. All these heat dissipations are aggregated in the dynamic sensing module, and the total dynamic load value is calculated using a formula that reflects the characteristics of heat load changes over time.

[0044] This invention comprehensively covers the impact of indoor heat sources. Traditional air conditioning systems often fail to respond in real time to changes in occupant behavior, equipment operation, and lighting, leading to control lag and decreased comfort. By integrating multiple sensing technologies, this invention achieves real-time monitoring and adjustment of dynamic factors. For example, when people gather in a meeting room or equipment is used extensively, the system rapidly increases cooling capacity; when lights are turned off or people leave, the system reduces output to avoid energy waste. This dynamic response not only improves the stability and comfort of the indoor environment but also significantly optimizes energy use and reduces carbon emissions. Furthermore, it supports personalized control, allocating resources according to the heat load requirements of different areas, improving system flexibility and reliability, making it suitable for dynamic environments such as schools and hospitals.

[0045] The server also includes a load trend prediction module, which includes a load identification module and a load prediction module. The load identification module is used to calculate the load at each moment according to the preset time interval, and to calculate the load change at each time interval; The load forecasting module is used to predict future load changes and obtain load demand based on historical data, current personnel data, environmental data, and various load changes. The regulation and control module is also used to generate supply and demand at corresponding times based on future load changes.

[0046] By using historical data and real-time analysis to predict future load changes, the air conditioning system achieves proactive control. The load trend prediction module includes a load identification module and a load prediction module: the load identification module calculates various loads at each moment according to preset time intervals and analyzes load change trends; the load prediction module combines historical data, current personnel data, environmental data, and load changes, using statistical or machine learning methods to predict future load demand. Based on these prediction results, the regulation and control module generates supply and demand at the corresponding time, enabling the air conditioning system to adjust its operating status in advance.

[0047] Overcoming the latency issues of traditional reactive control, which operates solely based on current conditions, often leads to energy spikes and equipment wear, this invention achieves smooth energy management and a more stable indoor environment by predicting load trends. For example, when it predicts a surge of people entering a space, the system can increase cooling capacity in advance to prevent a sudden temperature rise; when it predicts a decrease in load, the system can reduce output in advance to save energy. This predictive control not only improves energy efficiency and reduces operating costs but also extends the lifespan of air conditioning equipment and avoids frequent start-ups and shutdowns. Simultaneously, it enhances the system's adaptability, resulting in a more seamless and comfortable user experience, making it particularly suitable for locations with strong time-regularities, such as offices or schools, where load changes are highly predictable.

[0048] The personnel sensing module collects images of people through a camera, and obtains the posture, movement and number of people in the collection space by recognizing the images. It uses a Wi-Fi probe to determine the entry and exit of people, and a pressure sensor on the seat to detect whether people are seated.

[0049] This invention also discloses a dynamic control method for an air conditioning system based on human behavior, comprising the following steps: S1. Acquire personnel data and environmental data within the data collection area; S2. Generate the static load of the acquisition space based on the environmental data of the acquisition space; S3. Analyze the number of people, their behavior, and the behavior of facilities in the data collection space in real time based on the personnel data and environmental data in the data collection space, and generate the dynamic load of the data collection space based on the number of people, their behavior, and the behavior of facilities. S4. When the static load reaches the air conditioner start-up threshold, control the air conditioner to turn on and generate the supply demand of the collection space based on the dynamic load. S5. Based on the current supply demand of each space, determine the cooling or heating capacity and air volume of the air conditioning unit for each space and generate adjustment instructions, which are then sent to the air conditioning drive module. The equipment drive module is also used to generate adjustment instructions based on the fine-tuning amount.

[0050] S2 includes the following steps: S21. Pre-store the enclosure structure data of each acquisition space, wherein the enclosure structure data includes the heat transfer coefficient and area of ​​the enclosure structure of the acquisition space. S22. Based on the indoor and outdoor temperatures, obtain the indoor-outdoor temperature difference, and combine this with the data from the building envelope to obtain the static load of the space being surveyed.

[0051] in, This represents the heat transfer coefficient of the building envelope. Indicates the area of ​​the enclosure structure. This indicates the temperature difference between indoors and outdoors.

[0052] S3 includes the following steps: S31. Based on the images of people in the acquisition space, identify the activity intensity of the people in the acquisition space, and based on the number of people and the activity intensity of the people, identify the heat dissipation of the people. S32. Identify the heat dissipation of the devices in the acquisition space based on the device type and the on / off status of each device. S33. Identify the heat dissipation of the lighting in the acquisition space based on the activation device of the lighting equipment in the acquisition space; S34. Identify one or more of the air infiltration heat and solar radiation fluctuations in the acquisition space to obtain other dynamic loads; S35. Based on the heat dissipation from personnel, equipment, lighting, and other dynamic loads, the dynamic load is obtained:

[0053] This represents the total dynamic load at time t. This represents the amount of heat dissipated by the personnel at time t. This represents the amount of heat dissipated by the device at time t. This represents the amount of heat dissipated by the lighting at time t. This represents the other heat dissipation at time t.

[0054] It also includes the following steps: S61. Calculate the load at each moment according to the preset time interval, and calculate the load change at each time interval; S62. Based on historical data, current personnel data, environmental data, and various load changes, predict future load changes to obtain load demand; S63. Based on the load changes at future times, generate supply and demand at the corresponding times.

[0055] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A dynamic control system for an air conditioning system based on human behavior, characterized in that: It includes a server, a sensing module, and an air conditioning drive module. The sensing module includes a personnel sensing module and an environmental sensing module. The personnel sensing module is used to collect personnel data in the space, and the environmental sensing module is used to collect environmental data in the space. The server includes a data acquisition module, a static analysis module, a dynamic sensing module, an adjustment and control module, and an equipment drive module. The data acquisition module is used to acquire personnel data and environmental data from the sensing module. The static analysis module is used to generate the static load of the acquisition space based on the environmental data of the acquisition space. The dynamic sensing module is used to analyze the number of people, their behavior, and the behavior of facilities in the data collection space in real time based on the personnel data and environmental data in the data collection space, and to generate the dynamic load of the data collection space based on the number of people, their behavior, and the behavior of facilities. The adjustment and control module is used to control the air conditioner to turn on when the static load reaches the air conditioner start threshold, and to generate the supply demand of the collected space based on the dynamic load. The device driver module is used to determine the cooling or heating capacity and air volume of the air conditioning unit for each space based on the current supply demand of each space, and generate adjustment instructions, which are then sent to the air conditioning driver module. The device driver module is also used to generate adjustment instructions based on the fine-tuning amount. The dynamic sensing module includes a personnel sensing module, an equipment sensing module, a lighting sensing module, and other sensing modules; The personnel sensing module is used to identify the activity intensity of personnel in the acquisition space based on the images of personnel in the acquisition space, and to identify the heat dissipation of personnel based on the number of personnel and the activity intensity of personnel. The device sensing module is used to identify the heat dissipation of devices in the data acquisition space based on the device type and the on / off status of each device. The lighting sensing module is used to identify the amount of heat dissipation from lighting devices in the data collection space based on the activation status of these devices. Other sensing modules are used to identify one or more of the air infiltration heat and solar radiation fluctuations in the collection space to obtain other dynamic loads; The dynamic sensing module is used to obtain the dynamic load based on the heat dissipation of personnel, equipment, lighting, and other dynamic loads. This represents the total dynamic load at time t. This represents the amount of heat dissipated by the personnel at time t. This represents the amount of heat dissipated by the device at time t. This represents the amount of heat dissipated by the lighting at time t. This represents other heat dissipation at time t; The personnel perception module also includes a clothing thermal resistance recognition module, which is used to identify the clothing outline of personnel based on the personnel images in the acquisition space, and to identify the real-time clothing thermal resistance coefficient of each person by the coverage and volume of the clothing outline relative to a standard human body model. It also identifies and frames each independent human body region from the personnel images and performs visual feature analysis on each human body region. By analyzing the differences between pixels within the human body region and a preset skin color model, the area of ​​the body surface covered by clothing is identified, and the proportion of this area to the total area of ​​the human body region is calculated to obtain the body region coverage rate. By comparing the actual outer contour of the human body region with the contour of the benchmark human body model generated based on the human body posture, the contour deviation between the two in key torso and limb parts is measured to obtain the fabric contour fluffiness. By identifying pixels in the human body region that conform to preset skin color and texture characteristics, the proportion of exposed skin area to the total area is calculated to obtain the percentage of exposed skin area; Real-time clothing thermal resistance coefficient = W1 × body area coverage + W2 × clothing silhouette fluffiness - W3 × percentage of exposed skin area + baseline value; Among them, W1, W2, and W3 are weighting coefficients obtained by calibration based on experimental data, and the baseline value is preset to represent the basic thermal resistance of the lightest summer clothing. The dynamic sensing module is used to correct the heat dissipation of personnel based on the real-time thermal resistance coefficient of clothing. in This represents the corrected total heat dissipation from personnel, where n is the number of personnel. This is the basic unit heat dissipation calculated based on the activity intensity of the j-th person. This is the preset thermal resistance influence coefficient. Let be the thermal resistance coefficient of the clothing worn by the j-th person at time t; The adjustment and control module also includes a clothing change response module, which is used to monitor the rate of change of the average thermal resistance coefficient of clothing of people in the acquisition space. When the rate of change is lower than the preset negative threshold within the preset time window, it is determined that a collective clothing reduction event has occurred. When a collective clothing reduction event occurs, a phased heating command is generated. The phased heating command includes a temporary target temperature higher than the current set value and a transition time. The device drive module gradually adjusts the current set value to the temporary target temperature within the transition time according to the phased temperature increase command.

2. The dynamic control system for an air conditioning system based on human behavior according to claim 1, characterized in that: The environmental sensing module includes an indoor sensing module and an outdoor sensing module, and the static analysis module includes a structure management module; the indoor sensing module is used to acquire the indoor temperature in the acquisition space, and the outdoor sensing module is used to acquire the outdoor temperature. The structure management module pre-stores the enclosure structure data of each acquisition space, including the heat transfer coefficient and area of ​​the enclosure structure of the acquisition space. The static analysis module is used to obtain the indoor and outdoor temperature difference based on the indoor and outdoor temperatures, and to obtain the static load of the acquisition space by combining the data of the building envelope. in, Indicates the heat transfer coefficient of the building envelope. Indicates the area of ​​the enclosure structure. This indicates the temperature difference between indoors and outdoors.

3. The dynamic control system for an air conditioning system based on human behavior according to claim 1, characterized in that: The server also includes a load trend prediction module, which includes a load identification module and a load prediction module. The load identification module is used to calculate the load at each moment according to the preset time interval, and to calculate the load change at each time interval; The load forecasting module is used to predict future load changes and obtain load demand based on historical data, current personnel data, environmental data, and various load changes. The regulation and control module is also used to generate supply and demand at corresponding times based on future load changes.

4. The dynamic control system for an air conditioning system based on human behavior according to claim 3, characterized in that: The personnel sensing module collects images of people through a camera, and obtains the posture, movement and number of people in the collection space by recognizing the images. It uses a Wi-Fi probe to determine the entry and exit of people, and a pressure sensor on the seat to detect whether people are seated.

5. A dynamic control method for an air conditioning system based on human behavior, characterized in that: Includes the following steps: S1. Acquire personnel data and environmental data within the data collection area; S2. Generate the static load of the acquisition space based on the environmental data of the acquisition space; S3. Analyze the number of people, their behavior, and the behavior of facilities in the data collection space in real time based on the personnel data and environmental data in the data collection space, and generate the dynamic load of the data collection space based on the number of people, their behavior, and the behavior of facilities. S4. When the static load reaches the air conditioner start-up threshold, control the air conditioner to turn on and generate the supply demand of the collection space based on the dynamic load. S5. Based on the current supply demand of each space, determine the cooling or heating capacity and air volume of the air conditioning unit for each space and generate adjustment instructions, which are then sent to the air conditioning drive module. The equipment drive module is also used to generate adjustment instructions based on the fine-tuning amount.

6. The dynamic control method for an air conditioning system based on human behavior according to claim 5, characterized in that: S2 includes the following steps: S21. Pre-store the enclosure structure data of each acquisition space, wherein the enclosure structure data includes the heat transfer coefficient and area of ​​the enclosure structure of the acquisition space. S22. Based on the indoor and outdoor temperatures, obtain the indoor-outdoor temperature difference, and combine this with the data from the building envelope to obtain the static load of the space being surveyed. in, Indicates the heat transfer coefficient of the building envelope. Indicates the area of ​​the enclosure structure. This indicates the temperature difference between indoors and outdoors.

7. The dynamic control method for an air conditioning system based on human behavior according to claim 6, characterized in that: S3 includes the following steps: S31. Based on the images of people in the acquisition space, identify the activity intensity of the people in the acquisition space, and based on the number of people and the activity intensity of the people, identify the heat dissipation of the people. S32. Identify the heat dissipation of the devices in the acquisition space based on the device type and the on / off status of each device. S33. Identify the heat dissipation of the lighting in the acquisition space based on the activation device of the lighting equipment in the acquisition space; S34. Identify one or more of the air infiltration heat and solar radiation fluctuations in the acquisition space to obtain other dynamic loads; S35. Based on the heat dissipation from personnel, equipment, lighting, and other dynamic loads, the dynamic load is obtained: This represents the total dynamic load at time t. This represents the amount of heat dissipated by the personnel at time t. This represents the amount of heat dissipated by the device at time t. This represents the amount of heat dissipated by the lighting at time t. This represents the other heat dissipation at time t.

8. The dynamic control system and method for an air conditioning system based on human behavior according to claim 7, characterized in that: It also includes the following steps: S61. Calculate the load at each moment according to the preset time interval, and calculate the load change at each time interval; S62. Based on historical data, current personnel data, environmental data, and various load changes, predict future load changes to obtain load demand; S63. Based on the load changes at future times, generate supply and demand at the corresponding times.

Images