A multi-sensor data fusion-based heating, ventilation and air conditioning dynamic control system and method

Abstract

The application discloses a kind of based on multi-sensor data fusion's heating ventilation air conditioner dynamic control system and method, and collects indoor and outdoor environment information and indoor occupancy information;According to different privacy needs, room type is divided into low privacy requirement, medium privacy requirement, high privacy requirement and large space area four types;According to privacy requirement, select a variety of sensor combination detection to obtain indoor occupancy number;Calculate indoor air conditioning cold and heat load, and adjust air conditioning operating parameters by dynamic factor to indoor air conditioning cold and heat load correction, and dynamic factor is based on indoor and outdoor environment change factor, indoor equipment use change factor and indoor population change factor weighted summation obtained.The present application can more comprehensively perceive indoor and outdoor environment change and occupancy by integrating multiple types of sensors, and this comprehensive data acquisition and processing method enables air conditioning system to accurately adjust according to real-time data, optimizes energy utilization, and reduces unnecessary energy consumption.

Description

Technical Field

[0001] This invention belongs to the field of HVAC system control, specifically, it relates to a dynamic control system and method for HVAC based on multi-sensor data fusion. Background Technology

[0002] In modern building environments, the efficiency and precise control of heating, ventilation, and air conditioning (HVAC) systems are crucial for energy conservation, emission reduction, and improving indoor environmental quality. Traditional HVAC systems often rely on simplified control strategies, such as fixed temperature settings and timer operation, which are often unable to adapt to complex and changing indoor and outdoor environments, leading to energy waste and reduced comfort.

[0003] With technological advancements, the application of multi-sensor data fusion technology in HVAC systems has gained increasing attention. This technology comprehensively utilizes data collected from multiple sensors to provide more complete and accurate environmental information, thereby achieving more efficient system control. However, existing multi-sensor fusion methods still have shortcomings in the comprehensive processing of indoor and outdoor environmental data, accurate detection of occupancy, and real-time calculation of air conditioning heating and cooling loads.

[0004] First, most existing systems cannot fully utilize indoor and outdoor environmental data to optimize air conditioning system operation. Second, existing technologies for occupancy detection often rely on a single sensor type, such as infrared or video sensors, which limits the accuracy and applicability of the detection. For example, relying solely on video sensors is difficult to implement in environments with high privacy requirements. Finally, existing air conditioning load calculation models often use static analysis methods, which cannot reflect the impact of changing indoor and outdoor environmental conditions on cooling and heating loads in real time.

[0005] These shortcomings lead to reduced efficiency and increased energy consumption in HVAC systems, which is detrimental to achieving green energy conservation and improving indoor environmental quality. Summary of the Invention

[0006] The purpose of this invention is to address the shortcomings of existing technologies by proposing a dynamic control system and method for HVAC based on multi-sensor data fusion.

[0007] This invention is achieved through the following technical solution: a dynamic control system for HVAC based on multi-sensor data fusion, which includes an information acquisition unit, an information processing unit, a load calculation unit, a parameter calculation unit, and a terminal control unit;

[0008] The information collection unit collects indoor and outdoor environmental information and indoor occupancy information in real time;

[0009] The information processing unit is used to process the indoor occupancy information collected by the information collection unit. Based on different privacy requirements, the room type is divided into four types: low privacy requirement, medium privacy requirement, high privacy requirement, and large space area. Based on the privacy requirements, multiple sensor combinations are selected to detect the number of people occupying the room.

[0010] The load calculation unit calculates the indoor air conditioning cooling and heating load based on indoor and outdoor environmental information and the number of people occupying the room, and corrects the indoor air conditioning cooling and heating load through dynamic factors. The dynamic factors are obtained by weighted summation of indoor and outdoor environmental change factors, indoor equipment usage change factors, and indoor number of people change factors.

[0011] The parameter calculation unit calculates the operating parameters of the HVAC system based on the indoor air conditioning cooling and heating load.

[0012] The terminal control unit is used to adjust the operating parameters of the air conditioner according to the operating parameters of the HVAC system.

[0013] Furthermore, the indoor and outdoor environmental information is based on data collected from temperature and humidity sensors, solar radiation sensors, and smart sockets.

[0014] Furthermore, the indoor occupancy information is based on occupancy data collected from different types of rooms using cameras, pressure-sensitive carpet sensors, light interruption sensors, CO2 sensors, PIR sensors, or wireless sensors.

[0015] Furthermore, for rooms with low privacy requirements, cameras are used to output the number of people occupying the room in real time. For rooms with medium privacy requirements, a combination of cameras and CO2 sensors is used to calculate the number of people occupying the room using discrete differential equations. For rooms with high privacy requirements, pressure-sensitive carpet sensors and light interruption sensors are used. Based on the time difference between the signals from the two types of sensors, the entry and exit status of people is determined, and the number of people occupying the room is calculated. For large open areas, a combination of CO2 sensors, PIR sensors, and wireless sensors is used. An ANN model and a multiple linear regression model are used to fuse the sensor data and calculate the number of people occupying the area.

[0016] Furthermore, the process by which the load calculation unit calculates the indoor air conditioning cooling and heating load is as follows:

[0017] 1) Measure indoor and outdoor temperature and humidity using indoor and outdoor temperature sensors, and calculate the heat loss Q due to infiltration and ventilation. infiltration ; Calculate the heat gain Q through the building envelope by combining the area and heat transfer coefficient of the building envelope. conduction .

[0018] 2) The power of lights and devices is read through the smart socket, and the internal heat gain from the lights and devices is calculated based on the ledger information; the internal heat gain from people in the room is calculated based on the number of people in the room measured by the occupancy detection sensor; the two heat gain items are added together to obtain the internal heat gain Q. internal .

[0019] 3) Calculate the solar radiation gain Q of the transparent enclosure structure by measuring the solar radiation intensity using a solar radiation sensor and combining the area and heat transfer coefficient of the transparent enclosure structure. solar .

[0020] 4) Establish a heat balance model, add up all heat gains and heat losses to obtain the total heat load, and calculate it using the following formula:

[0021] Q total =Q infitration +Q conduction +Q internal +Q solar

[0022] 5) Introduce the dynamic factor DF to establish a dynamic heat balance model. This factor captures and quantifies real-time changes in the building's internal and external environment, such as occupant activity, equipment usage, and external climate conditions, reflecting the impact of real-time data changes on the heat load. The dynamic factor DF is calculated using the following formula:

[0023] DF = w1·F occupancy +w2·F equipment +w3·F external

[0024] F occupancy =N current ×100

[0025]

[0026] F external =ΔT×C T +ΔH×C H

[0027]

[0028] Among them, F occupancy N is the occupancy factor based on occupancy sensor data. current This represents the current number of people indoors; F equipment P is the device usage factor based on device data collected from smart sockets. t It is the power of device i, S t This represents the state of device i (0 indicates off, 1 indicates on), and n is the total number of indoor devices; F externalThe external environmental factors are based on data from temperature and humidity sensors and solar radiation sensors. ΔT is the difference between indoor and outdoor temperature, ΔH is the difference between indoor and outdoor relative humidity, and C is the value of C. T and C H These are the influence coefficients for temperature difference and humidity difference, respectively; w1, w2, and w3 are weighting coefficients, and X... i It is the historical dataset of factor i, and Y is the dataset with respect to X. i The corresponding dataset of air conditioning load response has weighting coefficients adjusted according to the degree of influence of sensor data on heat load; the dynamic heat load is calculated using the following formula:

[0029] Q total_dynamic =Q total (1+DF)

[0030] Among them, Q total_dynamic This is the total heat load after dynamic factor correction.

[0031] Furthermore, the parameter calculation unit selects the air volume and air temperature as the adjustment parameters for the HVAC dynamic control strategy. Based on the real-time cooling and heating load and humidity load of the air conditioner, the air volume and air temperature are calculated using the heat and humidity balance method.

[0032] On the other hand, the present invention also provides a dynamic control method for HVAC based on multi-sensor data fusion, the method comprising the following steps:

[0033] (1) Real-time collection of indoor and outdoor environmental information;

[0034] (2) Based on different privacy requirements, room types are divided into four types: low privacy requirements, medium privacy requirements, high privacy requirements, and large space areas; based on privacy requirements, multiple sensor combinations are selected to detect the number of people occupying the room.

[0035] (3) Calculate the indoor air conditioning cooling and heating load based on indoor and outdoor environmental information and the number of people occupying the room, and correct the indoor air conditioning cooling and heating load through dynamic factors. The dynamic factors are obtained by weighted summation of indoor and outdoor environmental change factors, indoor equipment usage change factors and indoor number of people change factors.

[0036] (4) Calculate the operating parameters of the HVAC system based on the indoor air conditioning cooling and heating load;

[0037] (5) Adjust the operating parameters of the air conditioner according to the operating parameters of the HVAC system.

[0038] The beneficial effects of this invention are as follows: By integrating multiple types of sensors, this method can more comprehensively perceive changes in the indoor and outdoor environment and occupancy status. This comprehensive data acquisition and processing approach enables the air conditioning system to precisely adjust based on real-time data, optimize energy utilization, and reduce unnecessary energy consumption. Particularly in terms of occupancy detection, this invention combines detection technologies with different privacy levels, such as the YOLOv8 algorithm and sensor fusion methods, ensuring the accuracy and adaptability of the detection. Furthermore, by establishing a dynamic air conditioning cooling and heating load calculation model, this method can accurately predict and respond to the impact of changes in the indoor and outdoor environment on air conditioning demand, thereby providing a more comfortable indoor environment. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a block diagram of the dynamic control system for HVAC based on multi-sensor data fusion of the present invention.

[0041] Figure 2 This is a flowchart of the dynamic control method for HVAC based on multi-sensor data fusion according to the present invention. Detailed Implementation

[0042] The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. The objectives and effects of the present invention will become clearer as a result. The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0043] like Figure 1 As shown, the present invention provides a dynamic control system for HVAC based on multi-sensor data fusion, specifically including an information acquisition unit, an information processing unit, a load calculation unit, a parameter calculation unit, and a terminal control unit.

[0044] The information collection unit is used to collect indoor and outdoor environmental information and indoor occupancy information in real time. The information collection unit includes an indoor and outdoor environmental information collection module and an indoor occupancy information collection module.

[0045] The indoor and outdoor environmental information acquisition module is used to collect outdoor temperature and humidity, solar radiation intensity, indoor temperature and humidity, operating power of lighting equipment and other equipment, and mainly includes temperature and humidity sensors, solar radiation sensors and smart sockets.

[0046] The indoor occupancy information acquisition module is used to collect indoor occupancy information by deploying different types of sensors according to the requirements of different types of rooms. These mainly include cameras, pressure-sensitive carpet sensors, light interruption sensors, CO2 sensors, PIR sensors, and wireless sensors.

[0047] The information processing unit is used to process the indoor occupancy information collected by the information acquisition unit, and can determine the number of people occupying the room based on data from different types of sensors. The information processing unit includes a low privacy requirement processing module, a medium privacy requirement processing module, a high privacy requirement processing module, and a large space area processing module.

[0048] The low privacy requirement processing module is used to process camera data from rooms with low privacy requirements and output the number of people occupying the room in real time. These low privacy requirement rooms are public or semi-public spaces with low privacy requirements, such as reception areas or open-plan office areas.

[0049] The aforementioned privacy requirement processing module processes data from cameras and CO2 sensors in rooms requiring privacy, and outputs the number of people occupying the room in real time. These rooms are semi-private spaces requiring a certain degree of privacy protection, such as meeting rooms, classrooms, small offices, and lounges.

[0050] The high privacy requirement processing module is used to process data from pressure-sensitive carpet and light interruption sensors in rooms with high privacy requirements, and outputs the number of people occupying the room in real time. These high privacy requirement rooms are private spaces with very high privacy protection requirements, such as personal offices, hospital wards, changing rooms, and dormitory rooms.

[0051] The large-space processing module is used to process data from CO2 sensors, PIR sensors, and wireless sensors in the large-space area, and output the number of people occupying the large-space area in real time. The large-space area refers to a large open space that can accommodate many people, such as a library reading room, restaurant, exhibition center, or large conference room.

[0052] The load calculation unit is used to calculate the indoor air conditioning cooling and heating load, and calculates the indoor air conditioning cooling and heating load based on the indoor and outdoor environmental information collected by the information acquisition unit and the number of people occupying the room output by the information processing unit.

[0053] The parameter calculation unit is used to calculate the operating parameters of the HVAC system based on the indoor air conditioning cooling and heating load obtained by the load calculation unit.

[0054] The terminal control unit is used to adjust the operating parameters of the air conditioner based on the received data.

[0055] like Figure 2 As shown, the present invention also provides a dynamic control method for HVAC based on multi-sensor data fusion, the system comprising:

[0056] S1. The information collection unit collects indoor and outdoor environmental information and indoor occupancy information in real time;

[0057] S2. The information processing unit calculates the number of people occupying the room based on data from different types of occupancy sensors and different types of rooms.

[0058] S3. The load calculation unit establishes an air conditioning cooling and heating load calculation model based on the dynamic heat balance method, reads data from various sensors and imports it into the air conditioning cooling and heating load calculation model based on the dynamic heat balance method, so as to realize the real-time calculation of indoor air conditioning cooling and heating load.

[0059] S4. The parameter calculation unit selects the air volume and air temperature as the adjustment parameters for the HVAC dynamic control strategy. Based on the real-time cooling and heating load and humidity load of the air conditioner, the air volume and air temperature are calculated using the heat and humidity balance method.

[0060] S5. The terminal control unit sends the received commands for adjusting the air supply volume and temperature to the air conditioning terminal to achieve dynamic control of the HVAC system.

[0061] Furthermore, the step in S2 of calculating the number of people occupying the room based on different types of room and different types of occupancy sensor data is as follows:

[0062] S21. For rooms with low privacy requirements, train the YOLOV8 algorithm to identify the number of people occupying the room from the RGB image, and then attach the information to a camera installed indoors to achieve real-time detection of the number of people occupying the room.

[0063] S22. For rooms with moderate privacy requirements, the YOLOv8 algorithm is trained to identify the number of people occupying the room from RGB images, and this information is then mounted on cameras installed at the room's entrance and exit. To reduce errors caused by lighting and camera angles, CO2 sensors are deployed to correct the image recognition results, and the number of people occupying the room is calculated using discrete differential equations.

[0064] S23. For rooms with high privacy requirements, pressure-sensitive carpets and light interruption sensors are installed at the room's entrances and exits to detect the number of people entering and exiting. Based on the time difference between the signals from the two sensors, the entry and exit status of personnel is determined, and the number of people occupying the room is calculated.

[0065] S24. For large open areas, a method of fusing CO2 sensors, PIR sensors, and Wi-Fi is adopted. An ANN model and a multiple linear regression model are used to fuse the sensor data and calculate the number of people occupying the area.

[0066] Furthermore, the step in S3 for real-time calculation of indoor air conditioning cooling and heating load is as follows:

[0067] S31. Measure indoor and outdoor temperature and humidity using indoor and outdoor temperature sensors, and calculate the heat loss Q due to infiltration and ventilation. infiltration ; Calculate the heat gain Q through the building envelope by combining the area and heat transfer coefficient of the building envelope. conduction .

[0068] S32. Read the power of lights and devices through the smart socket, and calculate the internal heat gain from lights and devices based on the ledger information; calculate the internal heat gain from people in the room based on the number of people in the room measured by the occupancy detection sensor; add the above two heat gain to obtain the internal heat gain Q. internal .

[0069] S33. Calculate the solar radiation gain Q of the transparent enclosure structure by measuring the solar radiation intensity using a solar radiation sensor and combining this with the area and heat transfer coefficient of the transparent enclosure structure. solar .

[0070] S34. Establish a heat balance model, add up all heat gains and heat losses to obtain the total heat load, and calculate it using the following formula:

[0071] Q total =Q infitration +Q conduction +Q internal +Q solar

[0072] S35. Introduce the dynamic factor DF to establish a dynamic heat balance model. This factor captures and quantifies real-time changes in the building's internal and external environment, such as occupant activity, equipment usage, and external climate conditions, reflecting the impact of real-time data changes on the heat load. The dynamic factor DF is calculated using the following formula:

[0073] DF = w1·F occupancy +w2·F equipment +w3·F external

[0074] F occupancy =N current ×100

[0075]

[0076] F external =ΔT×C T +ΔH×C H

[0077]

[0078] Among them, F occupancy N is the occupancy factor based on occupancy sensor data. current This represents the current number of people indoors; F equipment P is the device usage factor based on device data collected from smart sockets. t It is the power of device i, S t This represents the state of device i (0 indicates off, 1 indicates on), and n is the total number of indoor devices; F external The external environmental factors are based on data from temperature and humidity sensors and solar radiation sensors. ΔT is the difference between indoor and outdoor temperature, ΔH is the difference between indoor and outdoor relative humidity, and C is the value of C. T and C H These are the influence coefficients for temperature difference and humidity difference, respectively; w1, w2, and w3 are weighting coefficients, and X... i It is the historical dataset of factor i, and Y is the dataset with respect to X. i The corresponding dataset of air conditioning load response can have its weighting coefficients dynamically adjusted based on historical data and machine learning algorithms to optimize the air conditioning system's response. The dynamic heat load is calculated using the following formula:

[0079] Q total_dynamic =Q total ·(1+DF)

[0080] Among them, Q total_dynamic This is the total heat load after dynamic factor correction.

[0081] Furthermore, the step in S4 of calculating the air supply volume and air supply temperature using the heat and humidity balance method is as follows:

[0082] S41. Calculate the indoor humidity load by measuring the indoor humidity using a humidity sensor.

[0083] S42. Establish the heat balance equation and the moisture balance equation, and after simplification, obtain the heat-moisture ratio. Use the heat-moisture ratio process line on the enthalpy-humidity diagram to represent the state change process of the supplied air.

[0084] S43. Select the supply air temperature difference and air exchange rate, determine the indoor state point on the enthalpy-humidity chart, and draw the heat-humidity ratio line passing through the indoor state point based on the heat-humidity ratio.

[0085] S44. Based on the selected supply air temperature difference, determine the supply air state point on the heat-moisture ratio line, calculate the required supply air volume according to the equation obtained from the heat balance, and check the number of air changes.

[0086] The above embodiments are used to explain and illustrate the present invention, but not to limit the present invention. Any modifications and changes made to the present invention within the spirit and scope of the claims shall fall within the protection scope of the present invention.

Claims

1. A multi-sensor data fusion based HVAC dynamic control system, characterized in that, The system comprises an information acquisition unit, an information processing unit, a load calculation unit, a parameter calculation unit and a terminal control unit; The information acquisition unit acquires indoor and outdoor environment information and indoor occupancy information in real time; The information processing unit processes the indoor occupancy information acquired by the information acquisition unit, and divides room types into four types, i.e. low privacy requirement, medium privacy requirement, high privacy requirement and large space area, according to different privacy requirements; According to the privacy requirement, a plurality of sensor combinations are selected to detect the number of indoor occupants; The load calculation unit calculates indoor air conditioning cold and heat loads according to the indoor and outdoor environment information and the number of indoor occupants, and corrects the indoor air conditioning cold and heat loads through a dynamic factor, which is obtained by weighted summation of indoor and outdoor environment change factors, indoor equipment use change factors and indoor occupant number change factors; The parameter calculation unit calculates the operation parameters of the heating ventilation and air conditioning system according to the indoor air conditioning cold and heat loads; The terminal control unit adjusts the operation parameters of the air conditioner according to the operation parameters of the heating ventilation and air conditioning system.

2. The dynamic control system for heating, ventilation and air conditioning based on multi-sensor data fusion according to claim 1, characterized in that, The indoor and outdoor environment information is data acquired based on temperature and humidity sensors, solar radiation sensors and intelligent sockets.

3. The dynamic control system for heating, ventilation and air conditioning based on multi-sensor data fusion according to claim 1, characterized in that, The indoor occupancy information is occupancy information of different types of rooms acquired based on cameras, pressure sensor carpets, light interruption sensors, CO2 sensors, PIR sensors or wireless sensors.

4. The dynamic control system for heating, ventilation and air conditioning based on multi-sensor data fusion according to claim 1, characterized in that, For a room with low privacy requirement, a camera is used to output the number of occupants in the room in real time; for a room with medium privacy requirement, a camera and a CO2 sensor are combined to calculate the number of occupants in the room through a discrete differential equation; for a room with high privacy requirement, a pressure sensor carpet and a light interruption sensor are used to judge the personnel access state according to the time difference between the signals of the two sensors, and calculate the number of occupants in the room; for a large space area, a CO2 sensor, a PIR sensor and a wireless sensor are used, and an ANN model and a multiple linear regression model are used to fuse the sensor data to calculate the number of occupants in the area.

5. The HVAC dynamic control system based on multi-sensor data fusion of claim 1, wherein, The process of calculating the indoor air conditioning cold and heat loads by the load calculation unit is as follows: 1) Measure indoor and outdoor temperature and humidity by indoor and outdoor temperature and humidity sensors, calculate the heat loss Q of permeation and ventilation infiltration ; Calculate the heat gain Q by conduction through the building envelope combining the envelope area and the envelope heat transfer coefficient conduction ; 2) The power of light and equipment is read through the intelligent socket, and the internal heat gain from the light and equipment is calculated according to the account information; The internal heat gain from the human body is calculated according to the number of indoor occupants detected by the occupancy detection sensor; The internal heat gain Q is obtained by adding the above two heat gains internal ; 3) Calculate the solar radiation heat gain Q through and absorbed by the transparent envelope by measuring the solar radiation intensity with a solar radiation sensor, combining the transparent envelope area and the heat transfer coefficient solar ; 4) A heat balance model is established, all heat gains and heat losses are added to obtain the total heat load, which is calculated by the following formula: 5) A dynamic factor DF is introduced to establish a dynamic heat balance model; the factor captures and quantifies the real-time changes of the internal and external environment of the building, such as personnel activities, equipment usage, external climate conditions, and reflects the influence of real-time data changes on the heat load, which is calculated by the following formula: where F occupancy is the occupancy factor based on occupancy sensor data, N current is the current number of people in the room; F equipment is the device usage factor based on device data collected by smart sockets, P t is the power of device i, S t is the state of device i, S0 indicates that device i is in the off state, S1 indicates that device i is in the on state, and n is the total number of indoor devices; F external is the external environment factor based on temperature and humidity sensor, solar radiation sensor data, is the indoor-outdoor temperature difference, is the indoor-outdoor relative humidity difference, and are the influence coefficients of temperature difference and humidity difference, respectively; w1, w2, w3 are weight coefficients, is the historical data set of factor i, is the data set corresponding to the air conditioning load response of , and the weight coefficient is adjusted according to the influence degree of sensor data on thermal load; the dynamic thermal load is calculated by the following formula: wherein, Qtotal is the total heat load.

6. The HVAC dynamic control system based on multi-sensor data fusion of claim 1, wherein, The parameter calculation unit selects the air supply volume and air supply temperature as the adjustment parameters of the heating ventilation and air conditioning dynamic control strategy; according to the real-time cold and heat loads and the humidity load of the air conditioner, the air supply volume and air supply temperature are calculated by using the heat and humidity balance method.

7. A method for dynamic control of HVAC based on multi-sensor data fusion based on the system of any of claims 1-6, characterized in that, The method comprises the following steps: (1) Real-time acquisition of indoor and outdoor environment information; (2) According to different privacy requirements, the room types are divided into four types: low privacy requirement, medium privacy requirement, high privacy requirement and large space area; according to the privacy requirement, a plurality of sensor combinations are selected to detect the indoor occupancy number; (3) According to the indoor and outdoor environment information and the indoor occupancy number, the indoor air conditioning cold and heat load is calculated, and the indoor air conditioning cold and heat load is corrected through a dynamic factor, the dynamic factor being obtained by weighted summation of indoor and outdoor environment change factors, indoor equipment use change factors and indoor number change factors; (4) According to the indoor air conditioning cold and heat load, the operation parameters of the heating and ventilation air conditioning system are calculated; (5) According to the operation parameters of the heating and ventilation air conditioning system, the operation parameters of the air conditioner are adjusted.

Images