An intelligent central air conditioning integrated control method and system based on precise regulation

Abstract

The present invention relates to the field of central air-conditioning control technology, and more specifically, to an intelligent central air-conditioning integrated control method and system based on precise adjustment, which obtains user indoor image data and indoor temperature distribution data; obtains user historical usage data, the historical data including user preferred temperature settings, air-conditioning operation mode and time period; generates a user surface temperature distribution image based on the user indoor image data; determines the user surface temperature mean and the indoor temperature mean according to the indoor temperature distribution data and the user surface temperature distribution image, and determines a compensation temperature; based on the compensation temperature, compensates and adjusts a preset user temperature adjustment model; outputs the compensated user comfort temperature; generates control instructions for precise adjustment of the central air-conditioning to optimize the air-conditioning operation parameters in real time, and can dynamically adjust the air-conditioning operation parameters by capturing the user surface temperature characteristics in real time and combining them with indoor and outdoor environmental parameters, so as to achieve precise response to the user's personalized needs.

Description

Technical Field

[0001] The present invention relates to the technical field of central air-conditioning control, and more specifically, to an intelligent central air-conditioning integrated control method and system based on precise regulation. Background Art

[0002] With the development of HVAC technology, central air conditioning systems have been widely used due to their outstanding performance in efficient energy management and environmental comfort control in large buildings. However, traditional central air conditioning control methods are often based on static preset parameters or simple environmental feedback mechanisms, which are difficult to adapt to the diversity of user needs and the complexity of environmental conditions. The limitations of this control method are particularly reflected in the lack of real-time and accuracy, including the following issues:

[0003] First, the operational control of traditional central air conditioning systems primarily relies on single data inputs from environmental sensors (such as indoor temperature and humidity sensors), lacking specificity in understanding individual user needs. Because individual thermal comfort needs, such as body temperature, are difficult to capture effectively, adjustment strategies often deviate from actual needs. This "one-size-fits-all" approach not only easily leads to decreased user comfort but also wastes energy through unnecessary adjustments.

[0004] Secondly, existing central air conditioning systems lack effective intelligent algorithms to support the connection between environmental parameter acquisition and air conditioning control decisions. Most systems rely solely on simple rule-based control methods, failing to effectively integrate multi-source data (such as indoor and outdoor temperatures, user behavior, and usage history) to make optimal decisions. This approach is not only computationally cumbersome and unable to adapt to dynamic environmental changes, but also prone to lags in parameter adjustment, which can lead to reduced system efficiency.

[0005] Furthermore, traditional control methods are often based on static models, ignoring the dynamic nature of environmental parameters and user needs. Specifically, they lack dynamic calculation of the thermodynamic equilibrium between the user's body temperature and the ambient temperature, making it difficult for the system to achieve the desired regulatory effect. For example, when user activity intensity, location distribution, or ambient temperature and humidity fluctuate dramatically, the system cannot quickly adjust its regulation strategy, failing to ensure user comfort and potentially increasing equipment wear due to frequent switching.

[0006] Although the closest existing technologies have attempted to incorporate intelligent methods (such as limited fuzzy control or simple neural networks), they still have significant shortcomings in real-time data acquisition, accurate analysis, and dynamic decision-making optimization. Specifically, the limitations of these technologies are mainly reflected in the following aspects: First, existing methods cannot comprehensively analyze the synergistic relationship between the user's body surface temperature distribution and the indoor temperature distribution, and the compensation mechanism in the adjustment model is insufficient, making it difficult to achieve precise control; second, existing image processing technology is disconnected from the air conditioning adjustment mechanism, and it cannot form an effective perception-decision-execution closed loop; third, the parameter settings in the algorithm model are simple, and it fails to achieve dynamic adaptation to various environmental conditions and user behaviors. Summary of the Invention

[0007] In response to the above problems, the present invention starts from the core contradiction of central air-conditioning control and proposes an intelligent central air-conditioning integrated control method and system based on precise adjustment to make up for the shortcomings of the existing technology.

[0008] The present invention provides an intelligent central air-conditioning integrated control method based on precise regulation, comprising the following steps:

[0009] The acquisition steps include:

[0010] Acquire user indoor image data and indoor temperature distribution data, wherein the user indoor image data is used to reflect the user's body surface temperature characteristics, and the indoor temperature distribution data is used to reflect the ambient temperature changes;

[0011] Obtaining user historical usage data, including user preferred temperature settings, air conditioning operating modes, and time periods;

[0012] Processing steps include:

[0013] Based on the user's indoor image data, convert it from RGB color space to HSV color space, determine the brightness value of each pixel and perform cluster analysis, screen the user's body surface pixels, and generate the user's body surface temperature distribution image;

[0014] Determining the user's body surface temperature mean and the indoor temperature mean based on the indoor temperature distribution data and the user's body surface temperature distribution image, and further determining a compensation temperature;

[0015] Based on the compensation temperature, a compensation adjustment is performed on a preset user temperature adjustment model;

[0016] Output steps include:

[0017] Output compensated user comfort temperature;

[0018] Based on the user's comfortable temperature, control instructions for precise adjustment of the central air conditioner are generated to optimize the air conditioner operating parameters in real time.

[0019] Preferably, the obtaining step further comprises:

[0020] Obtain outdoor ambient temperature and humidity data;

[0021] The outdoor environment data is used as a weight factor to adjust parameters in the user temperature adjustment model.

[0022] Preferably, the processing steps specifically include:

[0023] According to the connected domain characteristics of the user's body surface pixels, the user's body surface pixels are divided into connected domains using a clustering algorithm, and the saturation value mean and information entropy value in each connected domain are calculated;

[0024] The connected domains whose entropy values ​​are greater than the preset threshold and whose saturation mean values ​​are within the set interval are selected as the user's body surface areas.

[0025] Preferably, the determination of the average user body surface temperature further comprises:

[0026] Calculate the temperature difference of each pixel by combining the Euclidean distance between the user's contour pixel and the geometric center point;

[0027] The temperature distribution of the user's body surface pixels is fitted and corrected through the neural network model.

[0028] Preferably, the determination of the compensation temperature specifically includes:

[0029] Generate a compensated temperature image according to the compensated temperature value of each pixel in the indoor temperature distribution image;

[0030] Based on the compensated temperature image, the compensated mean is calculated as the final compensated temperature.

[0031] Preferably, the compensation adjustment of the user temperature adjustment model specifically includes:

[0032] Adding each pixel value in the compensated image to the corresponding pixel value of the indoor temperature distribution image to generate a new temperature distribution image;

[0033] According to the new temperature distribution image, the operating parameters of the intelligent central air conditioner are adjusted, including the air outlet temperature and wind speed.

[0034] Preferably, the generation of the comfortable temperature specifically includes:

[0035] The user's comfortable temperature is generated based on the difference between the user's average body temperature and the average indoor temperature, combined with the preset temperature comfort model;

[0036] The temperature comfort model includes an outdoor temperature weight, a humidity weight, and a user personalized adjustment factor.

[0037] As an advantage, it further comprises:

[0038] Analyze historical operating data and dynamically update the weight factors of the temperature comfort model to adapt it to different seasons and environmental conditions.

[0039] As an advantage, it further comprises:

[0040] When the user is not indoors, the central air-conditioning operating parameters are optimized in combination with the outdoor temperature prediction model to enter energy-saving mode.

[0041] An intelligent central air-conditioning integrated control system based on precise regulation for executing the method described in the claims comprises:

[0042] Image acquisition module, used to obtain user indoor image data and indoor temperature distribution data;

[0043] a data processing module, configured to generate a user's body surface temperature distribution image based on the user's indoor image data, and determine a compensation temperature based on the indoor temperature distribution data and the user's body surface temperature distribution image;

[0044] an adjustment model module, configured to perform compensation adjustment on a user temperature adjustment model based on the compensation temperature;

[0045] A control module, configured to generate an operation control instruction for the central air conditioner according to the compensated user comfort temperature;

[0046] The data storage module is used to store historical user usage data and air conditioning operation logs to optimize subsequent adjustment strategies.

[0047] The present invention achieves dynamic adaptation of environmental parameters to individual needs by introducing multimodal data acquisition (such as user indoor image data and indoor temperature distribution data) and advanced algorithm models (including real-time compensation calculation of user body surface temperature average and indoor temperature average), fundamentally solving the problems of insufficient user demand perception and lack of dynamic decision-making ability in traditional methods.

[0048] The technical problem to be solved by the present invention is how to achieve accurate perception and dynamic response of the central air-conditioning system to the individual needs of users and changes in the indoor environment. By constructing a control mechanism based on image processing and multi-dimensional data analysis, the present invention not only effectively solves the contradiction between user comfort and energy efficiency in traditional methods, but also realizes the complementarity and collaborative optimization of multiple steps through algorithm design. For example, the clustering and screening mechanism of user surface temperature makes the extraction of user temperature features more accurate through clustering analysis based on HSV color space and connected domain screening technology; at the same time, the compensation mechanism of indoor and outdoor temperatures works together with the dynamic adjustment model to perform real-time compensation by calculating the difference between user surface temperature and indoor temperature, which significantly improves the accuracy of comfort calculation.

[0049] In terms of the collaborative design of steps and algorithms, this invention enables the system to adaptively adjust under varying environmental conditions through the combined optimization of compensation temperature and intelligent regulation models. For example, the calculation of compensation temperature not only integrates the user's body surface temperature distribution with the indoor temperature distribution, but also uses a neural network to fit and correct the dynamic temperature distribution, forming a complete perception-feedback closed loop. Simultaneously, the control instructions generated in the output stage further enhance the stability and accuracy of the regulation effect by optimizing the air conditioner's operating parameters (such as outlet temperature and wind speed) in real time.

[0050] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0051] 1. Accuracy: By capturing the user's body temperature characteristics in real time and combining it with indoor and outdoor environmental parameters, the system can dynamically adjust air conditioning operating parameters to accurately respond to the user's personalized needs.

[0052] 2. Dynamic adaptability: Based on the coordinated optimization of compensation temperature and regulation model, the present invention can adaptively adjust under different environmental conditions, significantly improving the stability and energy-saving efficiency of the system.

[0053] 3. High efficiency: By introducing multimodal data analysis and intelligent algorithms, the present invention forms a closed loop in the perception, calculation and execution links, significantly shortening the adjustment response time and improving operational efficiency.

[0054] 4. Energy saving: By combining the compensation mechanism with the energy-saving mode, the present invention can minimize unnecessary energy consumption while ensuring user comfort, thereby improving the overall energy efficiency of the system.

[0055] In summary, the method of the present invention overcomes the key defects in the existing technology through innovative data acquisition and processing technology, intelligent algorithm design and optimization of dynamic adjustment model, and provides an efficient and reliable solution for the intelligent development of central air-conditioning systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 Flow chart of the method of the present invention.

[0057] Figure 2 This is a data acquisition and processing logic diagram of the present invention.

[0058] Figure 3 This is a calculation logic diagram of the temperature compensation of the present invention.

[0059] Figure 4 This is the operating parameter adjustment logic diagram of the present invention.

[0060] Figure 5 This is a data storage and model optimization diagram of the present invention. DETAILED DESCRIPTION

[0061] Please refer to Figure 1-5 The present invention provides an intelligent central air-conditioning integrated control method based on precise regulation, comprising:

[0062] The acquisition steps include:

[0063] Acquire user indoor image data and indoor temperature distribution data, wherein the user indoor image data is used to reflect the user's body surface temperature characteristics, and the indoor temperature distribution data is used to reflect the ambient temperature changes;

[0064] Obtain user historical usage data, including user preferred temperature settings, air conditioning operating modes, and time periods.

[0065] Processing steps include:

[0066] Based on the user's indoor image data, convert it from RGB color space to HSV color space, determine the brightness value of each pixel and perform cluster analysis, screen the user's body surface pixels, and generate the user's body surface temperature distribution image;

[0067] Determining the user's body surface temperature mean and the indoor temperature mean based on the indoor temperature distribution data and the user's body surface temperature distribution image, and further determining a compensation temperature;

[0068] Based on the compensation temperature, a compensation adjustment is performed on a preset user temperature adjustment model.

[0069] Output steps include:

[0070] Output compensated user comfort temperature;

[0071] Based on the user's comfortable temperature, control instructions for precise adjustment of the central air conditioner are generated to optimize the air conditioner operating parameters in real time.

[0072] In a preferred embodiment of the present invention, image acquisition module 1 captures indoor image data, which reflects the user's body surface temperature characteristics, such as the size and distribution of the body's heat dissipation area. Simultaneously, temperature sensor module 2 collects indoor temperature distribution data to reflect the dynamic changes in ambient temperature. Data storage module 3 records historical user usage data, including the user's preferred temperature range, usage frequency, and patterns under different environmental conditions.

[0073] Preferably, in the method of the present invention, the HSV color space conversion of the image data adopts the following formula:

[0074]

[0075] Where H is the hue value, R, G, B are the red, green and blue values ​​of the pixel, and Δ is the difference between the maximum and minimum values. The hue and brightness values ​​of the pixels are classified by clustering algorithm, and combined with the brightness threshold (preferably 0.5, based on experience, this value can effectively avoid misjudgment of dark areas) to accurately screen out the user's body surface pixels. In the output stage, the average user's body surface temperature and the average indoor temperature are calculated using the formula:

[0076]

[0077] Among them, T comp To compensate for temperature, is the user's body surface temperature pixel value, is the indoor temperature pixel value, n and m are the number of skin temperature pixels and indoor temperature pixels, respectively. The generated compensation temperature is used to dynamically adjust the user's comfortable temperature through the temperature regulation model.

[0078] This step combines the user's actual needs with dynamic environmental changes through precise image data analysis and multi-dimensional temperature compensation calculations, making the control of central air conditioning more efficient and accurate.

[0079] In one embodiment of the present invention, the obtaining step further comprises:

[0080] Obtain outdoor ambient temperature and humidity data;

[0081] The outdoor environment data is used as a weight factor to adjust parameters in the user temperature adjustment model.

[0082] Preferably, in one embodiment of the present invention, outdoor temperature and humidity data are acquired in real time by the environmental data acquisition module 4. For example, when the outdoor temperature is lower than 10°C, the weight factor of the indoor conditioning model is automatically adjusted to:

[0083] W outdoor =0.8 (empirical value at low temperature)

[0084] When the humidity is above 70%, the humidity weighting factor is set to:

[0085] W humidtity =1.2 (empirical value under high humidity conditions)

[0086] These data are adjusted through dynamic weights, and the calculation formula for the user's comfortable temperature in the optimized temperature regulation model is:

[0087] T comfort =W outdoor ·T outdoor +W humidity H+W indoor ·T indoor

[0088] Among them, T comfort is the calculated user comfort temperature, T o utdoor,T indoor are the outdoor and indoor temperatures respectively, H is the humidity,

[0089] W outdoor W humidity ,W indoor They are dynamic weights respectively.

[0090] This method further improves the accuracy of user comfort and the adaptability of the model by increasing the dynamic influence of outdoor environmental parameters, making the operation of central air conditioning more in line with actual environmental requirements.

[0091] In one embodiment of the present invention, the processing steps specifically include:

[0092] According to the connected domain characteristics of the user's body surface pixels, the user's body surface pixels are divided into connected domains using a clustering algorithm, and the saturation value mean and information entropy value in each connected domain are calculated;

[0093] The connected domains whose entropy values ​​are greater than the preset threshold and whose saturation mean values ​​are within the set interval are selected as the user's body surface areas.

[0094] In a preferred embodiment of the present invention, based on the image connected domain algorithm, the connectivity between pixels is determined by calculating the Euclidean distance between adjacent pixels:

[0095]

[0096] Among them, d ij is the Euclidean distance between pixel points i and j, and x and y are pixel coordinates. ij <∈ (preferably, ∈=3 pixels, based on empirical values, this threshold is suitable for most scenes), then the two points belong to the same connected domain.

[0097] The entropy calculation formula for each connected domain is:

[0098]

[0099] Among them, E is the entropy value, p i is the probability density of the i-th pixel in the connected domain, and n is the total number of pixels in the connected domain. By screening connected domains with entropy values ​​greater than 2.5 and combining them with the condition that the saturation mean value is between 0.6 and 0.9, the user's body surface area can be effectively identified.

[0100] Through connected domain analysis and multi-condition screening, the accuracy of user surface area extraction is significantly improved, providing more reliable data support for subsequent temperature compensation calculations.

[0101] In a preferred embodiment of the present invention, determining the average user body surface temperature further includes:

[0102] Calculate the temperature difference of each pixel by combining the Euclidean distance between the user's contour pixel and the geometric center point;

[0103] The temperature distribution of the user's body surface pixels is fitted and corrected through the neural network model.

[0104] In a preferred embodiment of the present invention, the Euclidean distance from the user's contour pixel to the geometric center point is first calculated based on the distribution of the user's body surface pixels. The coordinates of the geometric center point are determined by the following formula:

[0105]

[0106] Among them, (x c ,y c ) is the coordinate of the geometric center point, x i ,y i is the coordinate of each pixel point on the body surface, and n is the total number of pixels on the user's body surface. The Euclidean distance of each pixel point is calculated as:

[0107]

[0108] Among them, d i is the Euclidean distance from pixel i to the geometric center. By calculating the temperature difference of each pixel:

[0109] ΔT i =T i -T avg

[0110] Among them, T i is the temperature value of pixel i, T avg It is the preliminarily calculated average user surface temperature.

[0111] Preferably, this method combines a neural network model to fit and correct the distribution of the user's body surface temperature. The input of the model is the Euclidean distance and the temperature difference of the pixel points, and the output is the corrected temperature value. The loss function of the neural network is defined as:

[0112]

[0113] Among them, T′ i is the output temperature value of the neural network, T i is the actual measurement value, and the goal of the loss function is to minimize the fitting error.

[0114] Through the distance calculation of the geometric center points and the fitting correction of the neural network, this method can effectively eliminate the influence of the deviation between pixel points, making the calculation of the user's body surface temperature more accurate and providing high-precision basic data for subsequent temperature compensation.

[0115] In a preferred embodiment of the present invention, the determination of the compensation temperature specifically includes:

[0116] Generate a compensated temperature image according to the compensated temperature value of each pixel in the indoor temperature distribution image;

[0117] Based on the compensated temperature image, the compensated mean is calculated as the final compensated temperature.

[0118] In a preferred embodiment of the present invention, the compensation temperature determination process first requires processing the indoor temperature distribution image and calculating the compensation temperature value of each pixel. The specific formula is as follows:

[0119] T comp (xy) = T room (x,y)+ΔT user

[0120] Among them, T comp (x, y) is the temperature value of the pixel (x, y) in the compensated temperature image, T room (x, y) is the temperature value of the corresponding pixel in the indoor temperature distribution image, ΔT user It is the compensation value of the user's body surface temperature.

[0121] Next, based on the compensated temperature values ​​of all pixels, the compensated mean is calculated:

[0122]

[0123] Among them, T comp_avg is the final compensated temperature, and m is the total number of pixels in the compensated temperature image.

[0124] By generating a compensated temperature image and calculating its mean, this method can dynamically reflect the comprehensive difference between the indoor temperature distribution and the user's body surface temperature, making the calculation of the compensated temperature more holistic and real-time, ensuring a more accurate central air-conditioning adjustment effect.

[0125] In a preferred embodiment of the present invention, the compensation adjustment of the user temperature adjustment model specifically includes:

[0126] Adding each pixel value in the compensated image to the corresponding pixel value of the indoor temperature distribution image to generate a new temperature distribution image;

[0127] According to the new temperature distribution image, the operating parameters of the intelligent central air conditioner are adjusted, including the air outlet temperature and wind speed.

[0128] Preferably, in the method of the present invention, the compensation adjustment process first superimposes the compensated temperature image and the indoor temperature distribution image pixel by pixel to form a new temperature distribution image, the formula of which is:

[0129] T new (xy) = T comp (x,y)+T room (x,y)

[0130] Among them, T new (x, y) is the temperature value of the pixel (x, y) in the new temperature distribution image, T comp (x,y) and T room (x, y) are the temperature values ​​of the corresponding pixels in the compensated temperature image and the indoor temperature distribution image respectively.

[0131] According to the new temperature distribution image, the intelligent central air conditioner adjusts the air outlet temperature and wind speed through the operating parameter adjustment module. Preferably, when the highest temperature point in the new temperature distribution image is higher than the set threshold (such as 28°C, based on the user's experience of comfortable temperature), the system will lower the air outlet temperature to 22°C and increase the wind speed to level 3 (the experience value is suitable for rapid heat dissipation). On the contrary, when the lowest temperature point is lower than the set threshold (such as 18°C), the air outlet temperature will be adjusted to 26°C and the wind speed will be reduced to level 1.

[0132] By superimposing the compensation image and the indoor temperature distribution image and adjusting the operating parameters of the central air conditioner in real time, this method can quickly respond to environmental changes and provide users with a more comfortable indoor environment.

[0133] In a preferred embodiment of the present invention, the generation of the comfortable temperature specifically includes: generating the user comfortable temperature based on the difference between the average user surface temperature and the average indoor temperature in combination with a preset temperature comfort model;

[0134] The temperature comfort model includes an outdoor temperature weight, a humidity weight, and a user personalized adjustment factor.

[0135] In a preferred embodiment of the present invention, the user's comfortable temperature is generated based on the following temperature comfort model:

[0136] T comfort =w outdoor ·T outdoor +w humidity H+w indoor ·T indoor +w user ΔT user

[0137] Among them, T comfort For user comfort temperature, T outdoor 、T indoor are outdoor and indoor temperatures respectively, H is humidity, ΔT user is the difference between the user's body surface temperature and the indoor temperature; w outdoor 、w humidity ,w indoor 、w user is the corresponding weight factor.

[0138] Preferably, the initial value of the weight factor is set based on experience as:

[0139] w outdoor =0.2,w humidity =0.3,w indoor =0.4,w user =0.1

[0140] The system dynamically adjusts the weighting factors based on environmental changes and user historical preferences to ensure the adaptability of comfortable temperature generation.

[0141] By comprehensively considering multi-dimensional environmental data and user personalized needs, the temperature comfort model of this method can accurately generate user comfort temperature, improving the intelligence level of central air-conditioning control and user experience.

[0142] In a preferred embodiment of the present invention, the method further comprises: analyzing historical operating data and dynamically updating the weight factors of the temperature comfort model to adapt the model to different seasons and environmental conditions.

[0143] In a preferred embodiment of the present invention, the system dynamically collects historical operating data, including indoor and outdoor temperature, humidity, and actual user-adjusted parameters, through an operation log unit. Based on this data, a dynamic weight update algorithm based on recursive least squares (RLS) is used to adjust the weight factors in the thermal comfort model.

[0144] Preferably, the core algorithm for dynamic weight update is as follows:

[0145]

[0146]

[0147] Among them, w t is the current weight factor vector, P t is the update matrix, x t is the input feature vector (such as outdoor temperature, humidity and user surface temperature data), y t is the actual comfort data, and λ is the forgetting factor, which is usually set to 0.95 to retain the influence of the most recent data.

[0148] Preferably, the method uses the above algorithm to adjust the weight factor in seasonal changes (such as high outdoor temperature and high humidity in summer) and dynamic environmental fluctuations (such as sudden temperature drop), so that the output of the temperature comfort model is closer to the actual needs of users.

[0149] By introducing the recursive least squares method to dynamically adjust the model weights, this method can effectively adapt to changes in the environment and user needs during long-term operation, thereby improving the intelligence level of the system and user comfort.

[0150] In a preferred embodiment of the present invention, it further includes: when the user is not indoors, combining the outdoor temperature prediction model, optimizing the central air-conditioning operating parameters and entering the energy-saving mode.

[0151] The method of the present invention preferably includes two main processes: user detection and air conditioning operation state optimization. When the system detects that a user has left the room, it uses the user behavior detection module to identify the indoor vacancy state, and then adjusts the air conditioning operation parameters in combination with the outdoor temperature prediction model to put the system into energy-saving mode.

[0152] Preferably, the outdoor temperature prediction model adopts a time series prediction method and uses an ARIMA model, whose core formula is:

[0153]

[0154] Among them, T t is the outdoor temperature at the predicted time point, φ i is the AR coefficient, θ j is the MA part coefficient, ∈ t is the noise term, p and q are the lag order and moving average order respectively.

[0155] In energy-saving mode, the following operating parameters are preferably set:

[0156] The upper limit of the air outlet temperature is adjusted to 28°C, which is suitable for energy-saving mode when the user is away;

[0157] The wind speed is reduced to level 1 to reduce energy consumption;

[0158] If the predicted outdoor temperature is lower than 15°C, the cooling function will be turned off and only the ventilation function will be turned on.

[0159] By combining user behavior detection with the outdoor temperature prediction model, this method effectively reduces energy consumption in an unmanned state while maintaining suitable basic indoor environmental conditions, taking into account both energy saving and actual needs.

[0160] In a preferred embodiment of the present invention, an intelligent central air-conditioning integrated control system based on precise regulation includes:

[0161] Image acquisition module 1, used to obtain user indoor image data and indoor temperature distribution data;

[0162] a data processing module 2, configured to generate a user's body surface temperature distribution image based on the user's indoor image data, and determine a compensation temperature based on the indoor temperature distribution data and the user's body surface temperature distribution image;

[0163] An adjustment model module 3 is configured to perform compensation adjustment on the user temperature adjustment model based on the compensation temperature;

[0164] Control module 4, used to generate an operation control instruction of the central air conditioner according to the compensated user comfort temperature;

[0165] The data storage module 5 is used to store historical user usage data and air conditioner operation logs to optimize subsequent adjustment strategies.

[0166] The system of the present invention includes an image acquisition module 1, which is connected to a high-resolution camera, preferably equipped with an infrared thermal imaging sensor, to collect data on the user's body surface temperature and indoor temperature distribution. A data processing module 2, using a built-in clustering algorithm and neural network model, processes the collected data into an image of the user's body surface temperature distribution. The data is then combined with the indoor temperature distribution image to calculate the compensation temperature.

[0167] The adjustment model module 3 preferably includes a dynamic adjustment unit, which receives the compensation temperature from the data processing module and adjusts the temperature adjustment model based on historical user usage data and environmental parameters. The control module 4 optimizes the operating status of the central air conditioner in real time by generating specific operation control instructions (such as adjusting the air outlet temperature and wind speed). The data storage module 5 is used to store historical user data and operation logs, and preferably also includes cloud-based remote synchronization capabilities to ensure operational data sharing across multiple devices.

[0168] Through multi-module collaboration, this system achieves precise adjustment and intelligent control, especially the user comfort temperature calculation and energy-saving strategy based on dynamic adjustment, which fully improves the intelligence level and user experience of the central air-conditioning system and provides comprehensive technical support for energy saving and user comfort.

[0169] It should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent central air conditioning integrated control method based on precise regulation, characterized in that: include: The acquisition steps include: Acquire user indoor image data and indoor temperature distribution data, wherein the user indoor image data is used to reflect the user's body surface temperature characteristics, and the indoor temperature distribution data is used to reflect the ambient temperature changes; Obtaining user historical usage data, wherein the user historical usage data includes user preferred temperature settings, air conditioning operating modes, and time periods; Processing steps include: Based on the user's indoor image data, convert it from RGB color space to HSV color space, determine the brightness value of each pixel and perform cluster analysis, screen the user's body surface pixels, and generate the user's body surface temperature distribution image; Determining the user's body surface temperature mean and the indoor temperature mean based on the indoor temperature distribution data and the user's body surface temperature distribution image, and further determining a compensation temperature; Based on the compensation temperature, a compensation adjustment is performed on a preset user temperature adjustment model; Output steps include: Output compensated user comfort temperature; Generate control instructions for precise adjustment of central air conditioning based on the user's comfortable temperature to optimize air conditioning operating parameters in real time; The processing steps specifically include: According to the connected domain characteristics of the user's body surface pixels, the user's body surface pixels are divided into connected domains using a clustering algorithm, and the saturation value mean and information entropy value in each connected domain are calculated; The connected domains whose entropy values ​​are greater than the preset threshold and whose saturation mean values ​​are within the set interval are selected as the user's body surface areas.

2. The intelligent central air conditioning integrated control method based on precise regulation according to claim 1 is characterized in that: The obtaining step further comprises: Obtain outdoor ambient temperature and humidity data; The outdoor ambient temperature and humidity data are used as weight factors to adjust the parameters in the user temperature regulation model.

3. The intelligent central air conditioning integrated control method based on precise regulation according to claim 1 is characterized in that: The determination of the user's body surface temperature mean further includes: Calculate the temperature difference of each pixel by combining the Euclidean distance between the user's contour pixel and the geometric center point; The temperature distribution of the user's body surface pixels is fitted and corrected through the neural network model.

4. The intelligent central air conditioning integrated control method based on precise regulation according to claim 1 is characterized in that: The determination of the compensation temperature specifically includes: Generate a compensated temperature image according to the compensated temperature value of each pixel in the indoor temperature distribution image; Based on the compensated temperature image, the compensated mean is calculated as the final compensated temperature.

5. The intelligent central air conditioning integrated control method based on precise regulation according to claim 1 is characterized in that: The compensation adjustment of the user temperature regulation model specifically includes: Adding each pixel value in the compensated image to the corresponding pixel value of the indoor temperature distribution image to generate a new temperature distribution image; According to the new temperature distribution image, the operating parameters of the intelligent central air conditioner are adjusted, including the air outlet temperature and wind speed.

6. The intelligent central air conditioning integrated control method based on precise regulation according to claim 1 is characterized in that: The generation of the comfortable temperature specifically includes: The user's comfortable temperature is generated based on the difference between the user's average body temperature and the average indoor temperature, combined with the preset temperature comfort model; The temperature comfort model includes an outdoor temperature weight, a humidity weight, and a user personalized adjustment factor.

7. The intelligent central air conditioning integrated control method based on precise regulation according to claim 6 is characterized in that: Further including: Analyze historical operating data and dynamically update the weight factors of the temperature comfort model to adapt it to different seasons and environmental conditions.

8. The intelligent central air conditioning integrated control method based on precise regulation according to claim 1 is characterized in that: Further including: When the user is not indoors, the central air-conditioning operating parameters are optimized in combination with the outdoor temperature prediction model to enter energy-saving mode.

9. An intelligent central air-conditioning integrated control system based on precise regulation, which implements the method according to any one of claims 1 to 8, characterized in that: include: Image acquisition module, used to obtain user indoor image data and indoor temperature distribution data; a data processing module, configured to generate a user's body surface temperature distribution image based on the user's indoor image data, and determine a compensation temperature based on the indoor temperature distribution data and the user's body surface temperature distribution image; an adjustment model module, configured to perform compensation adjustment on a user temperature adjustment model based on the compensation temperature; A control module, configured to generate an operation control instruction for the central air conditioner according to the compensated user comfort temperature; The data storage module is used to store historical user usage data and air conditioning operation logs to optimize subsequent adjustment strategies.

Images