Temperature controller intelligent adjusting method and system based on multi-source environment perception

Abstract

The invention relates to the field of temperature control adjustment, and discloses a temperature controller intelligent adjustment method and system based on multi-source environmental perception, which are used for solving the problems of inaccurate control, poor comfort and energy waste when data perception is single. Comprising the steps that a temperature comfort index, a humidity comfort index, an air comfort index and an illumination comfort index are calculated, a comprehensive comfort index is obtained through weighted summation, the comprehensive comfort index is compared with a preset threshold value to judge whether temperature control adjustment is started or not, and when the comprehensive comfort index is larger than or equal to an environment comfort threshold value, indoor temperature control does not need to be adjusted; when the comprehensive comfort degree index is smaller than an environment comfort degree threshold value, indoor temperature control is adjusted, a machine learning model is further introduced, the environment change trend is predicted through historical data, dynamic and self-adaptive temperature control adjustment is achieved in combination with user personalized preferences, the method can comprehensively and accurately evaluate the environment comfort degree, and the user experience is improved. And the intelligent level and the user experience of the temperature control system are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of thermostat adjustment, and more specifically to a method and system for intelligent thermostat adjustment based on multi-source environmental sensing. Background Technology

[0002] Existing temperature control systems typically rely on a single environmental data point, primarily using temperature as the sole basis for control. This "single-data perception" approach has several limitations. First, while temperature is an important indicator of environmental comfort, it is not the only factor. Environmental factors such as humidity, air quality, light intensity, and airflow also significantly impact human comfort perception. Traditional temperature control systems often overlook the role of these factors, adjusting heating or cooling equipment based on a set temperature value, resulting in imprecise environmental regulation. Because other environmental variables besides temperature are ignored, the system's response is usually lagging and unable to adapt to actual needs promptly. In high-humidity environments, although temperature... While humidity may be suitable, people may still feel uncomfortable. Traditional systems struggle to respond effectively to humidity changes, ultimately impacting overall comfort. Furthermore, due to overly simplistic control, systems rely excessively on temperature data, leading to energy waste. Temperature control devices may continue operating even when humidity is high but the set temperature is met, resulting in unnecessary energy consumption. This "single-data-sensing" control method not only reduces indoor comfort but also increases energy consumption, affecting the system's overall efficiency and sustainability. Therefore, existing temperature control systems need to comprehensively sense and adjust multiple environmental factors to improve system adaptability, accuracy, and energy efficiency.

[0003] However, the above-mentioned technologies have at least the following technical problems: Existing temperature control systems suffer from the problem of "single data perception," which leads to inaccurate control, poor comfort, and energy waste due to reliance solely on temperature data. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for intelligent adjustment of temperature controller based on multi-source environmental perception, so as to solve the problems existing in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A method for intelligent temperature control based on multi-source environmental perception includes the following steps: Step 1, acquiring temperature data, humidity data, air quality data, and light intensity data through temperature sensors, humidity sensors, air quality sensors, and light intensity sensors; Step 2, calculating temperature comfort index, humidity comfort index, air comfort index, and light comfort index using the temperature data, humidity data, air quality data, and light intensity data, and calculating a comprehensive comfort index from these indices, determining whether temperature control adjustment is needed based on the comprehensive comfort index; Step 3, if temperature control adjustment is determined to be needed, dynamically monitoring environmental changes using a machine learning model and predicting environmental change trends over a future period to obtain the environmental change trend; Step 4, performing personalized temperature control adjustment based on the environmental change trend and the user's comfort needs, combined with the environmental comfort index and individual preference data.

[0006] Preferably, the steps for obtaining the comprehensive comfort index are as follows: acquiring temperature data, including ambient air temperature, suitable temperature setpoint, temperature uniformity, ground temperature, radiant temperature, and heat source temperature, and evaluating the temperature comfort index based on the temperature data; acquiring humidity data, including indoor humidity, target humidity setpoint, humidity gradient value within the current time period, ground humidity, air humidity and airflow, and the influence of local moisture sources, and evaluating the humidity comfort index based on the humidity data; and acquiring air quality data, including fine particulate matter concentration, carbon dioxide concentration, and volatile organic compound (VOC) concentration. The concentration of volatile organic compounds and the air circulation index are used to assess the air comfort index based on air quality data. Light intensity data is obtained, including ambient light perception, target comfortable light value, light distribution uniformity, and natural light perception. The light comfort index is assessed based on the light intensity data. The temperature comfort index, humidity comfort index, air comfort index, and light comfort index are normalized, and the normalized temperature comfort index, humidity comfort index, air comfort index, and light comfort index are weighted and summed to obtain the comprehensive comfort index.

[0007] Preferably, the step of obtaining the temperature comfort index is as follows: obtaining the ambient air temperature and the suitable temperature setpoint from the temperature data, and calculating the temperature deviation coefficient by comparing the ambient air temperature and the suitable temperature setpoint; obtaining the suitable temperature setpoint and temperature uniformity from the temperature data, and calculating the temperature uniformity coefficient by comparing the suitable temperature setpoint and the temperature uniformity; obtaining the temperature uniformity and ground temperature value from the temperature data, and calculating the ground temperature coefficient by comparing the temperature uniformity and the ground temperature value; obtaining the ground temperature value and radiation... The radiant temperature coefficient is calculated by comparing the ground temperature value with the radiant temperature value in the temperature data. The heat source temperature coefficient is calculated by comparing the radiant temperature value with the heat source temperature value in the temperature data. The heat source adjustment coefficient is calculated by comparing the heat source temperature value with the suitable temperature setting value in the temperature data. Finally, the temperature comfort index is calculated using the temperature deviation coefficient, temperature uniformity coefficient, ground temperature coefficient, radiant temperature coefficient, heat source temperature coefficient, and heat source adjustment coefficient.

[0008] Preferably, the steps for obtaining the humidity comfort index are as follows: Obtain the indoor humidity value and suitable humidity range from the humidity data; calculate the humidity deviation coefficient by comparing the indoor humidity value and suitable humidity range; obtain the target humidity setpoint and tolerance of the target humidity setpoint from the humidity data; calculate the humidity setting range coefficient by comparing the target humidity setpoint and tolerance of the target humidity setpoint; obtain the initial humidity value and final humidity value of a historical time period from the humidity data; calculate the humidity change rate of the historical time period by comparing the initial humidity value and final humidity value; obtain the humidity gradient value, humidity change rate of the current time period, and humidity change rate of a historical time period from the humidity data; calculate the humidity fluctuation amplitude coefficient by comparing the humidity gradient value, humidity change rate of the current time period, and humidity change rate of a historical time period. The specific steps are as follows: In the formula This is the humidity fluctuation amplitude coefficient. This represents the humidity gradient value within the current time period. This represents the rate of change in humidity over the current time period. The system calculates the humidity variation rate over a historical period; it also obtains the difference between ground humidity and ambient humidity values ​​from the humidity data, and calculates the ground humidity deviation coefficient by comparing these differences; it obtains air humidity, airflow velocity, and humidity stability from the humidity data, and calculates the air humidity and airflow interaction coefficient by comparing these ratios; it obtains the local humidity source influence and humidity source influence intensity from the humidity data, and calculates the local humidity source comfort correction coefficient by comparing these ratios; and it normalizes the humidity deviation coefficient, humidity setting range coefficient, humidity fluctuation amplitude coefficient, ground humidity deviation coefficient, air humidity and airflow interaction coefficient, and local humidity source comfort correction coefficient. Finally, it calculates the humidity comfort index by normalizing the normalized humidity deviation coefficient, humidity setting range coefficient, humidity fluctuation amplitude coefficient, ground humidity deviation coefficient, air humidity and airflow interaction coefficient, and local humidity source comfort correction coefficient.

[0009] Preferably, the steps for obtaining the air comfort index are as follows: obtaining the fine particulate matter concentration and air quality standard from the air quality data, and calculating the air quality index by comparing the fine particulate matter concentration and the air quality standard; obtaining the carbon dioxide concentration and carbon dioxide concentration threshold from the air quality data, and calculating the carbon dioxide impact index by comparing the carbon dioxide concentration and the carbon dioxide concentration threshold from the air quality data; obtaining the volatile organic compound (VOC) concentration and VOC concentration threshold from the air quality data, and calculating the VOC impact index by comparing the VOC concentration and the VOC concentration threshold from the air quality data; obtaining the air circulation index and standard circulation index from the air quality data, and calculating the air circulation impact index by comparing the air circulation index and the standard circulation index from the air quality data; normalizing the air quality index, carbon dioxide impact index, organic compound impact index, and air circulation impact index, and calculating the air comfort index from the normalized air quality index, carbon dioxide impact index, organic compound impact index, and air circulation impact index.

[0010] Preferably, the step of obtaining the lighting comfort index is as follows: obtaining the ambient lighting perception and target lighting intensity values ​​from the lighting intensity data, and calculating the ratio of the ambient lighting perception and target lighting intensity values ​​to obtain the ambient lighting perception deviation index; obtaining the target comfortable lighting value and standard comfortable lighting range from the lighting intensity data, and calculating the ratio of the target comfortable lighting value and standard comfortable lighting range to obtain the lighting target compliance index; obtaining the lighting distribution uniformity and uniformity standard from the lighting intensity data, and calculating the ratio of the ambient lighting perception and target lighting intensity values ​​to obtain the target comfortable lighting compliance index; and obtaining the lighting distribution uniformity and uniformity standard from the lighting intensity data. The light uniformity index is calculated by comparing the uniformity of light distribution with the uniformity standard. The natural light perception index and the preset natural light standard are obtained from the light intensity data, and their ratios are calculated to obtain the natural light comfort index. The light perception deviation index, light target conformity index, light uniformity index, and natural light comfort index are normalized, and the normalized light perception deviation index, light target conformity index, light uniformity index, and natural light comfort index are used to calculate the light comfort index.

[0011] Preferably, the step of determining whether temperature control adjustment is needed based on the comprehensive comfort index is as follows: determine whether temperature control adjustment is needed based on the comprehensive comfort index; when the comprehensive comfort index is greater than or equal to the environmental comfort threshold, indoor temperature control does not need to be adjusted; when the comprehensive comfort index is less than the environmental comfort threshold, indoor temperature control is adjusted.

[0012] Preferably, a multi-source environmental sensing-based intelligent temperature controller adjustment system includes: a data acquisition module for acquiring temperature data, humidity data, air quality data, and light intensity data through temperature sensors, humidity sensors, air quality sensors, and light intensity sensors; a data processing module for calculating temperature comfort index, humidity comfort index, air comfort index, and light comfort index from the temperature data, humidity data, air quality data, and light intensity data, and calculating a comprehensive comfort index from the temperature comfort index, and determining whether temperature control adjustment is needed based on the comprehensive comfort index; a personalized demand analysis and adjustment module for dynamically monitoring environmental changes and predicting environmental change trends over a future period if temperature control adjustment is determined to be needed, using a machine learning model; and an optimization and feedback adjustment module for performing personalized temperature control adjustment based on environmental change trends and user comfort needs, combined with environmental comfort index and individual preference data.

[0013] The technical effects and advantages of this invention are as follows: By calculating the temperature comfort index, humidity comfort index, air comfort index, and light comfort index, and then weighting and summing them to obtain the comprehensive comfort index, a decision is made to determine whether to activate temperature control. When the comprehensive comfort index is greater than or equal to the environmental comfort threshold, no adjustment is needed for indoor temperature control. When the comprehensive comfort index is less than the environmental comfort threshold, the indoor temperature control is adjusted. Furthermore, a machine learning model is introduced to predict environmental change trends using historical data and combined with user personalized preferences to achieve dynamic and adaptive temperature control. This method can comprehensively and accurately assess environmental comfort, effectively improving the intelligence level of the temperature control system and the user experience. Attached Figure Description

[0014] Figure 1 A flowchart illustrating a method for intelligent temperature control based on multi-source environmental perception, provided in an embodiment of this application.

[0015] Figure 2 This is a structural diagram of a temperature controller intelligent adjustment system based on multi-source environmental perception, provided in an embodiment of this application. Detailed Implementation

[0016] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The intelligent adjustment method and system for temperature controllers based on multi-source environmental perception involved in the present invention are not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] This invention provides a method for intelligent temperature control based on multi-source environmental sensing, such as... Figure 1 As shown, it includes the following steps: Step 1: Acquire temperature data, humidity data, air quality data, and light intensity data using temperature sensors, humidity sensors, air quality sensors, and light sensors.

[0018] Step 2: Calculate the temperature comfort index, humidity comfort index, air comfort index, and light comfort index using temperature data, humidity data, air quality data, and light intensity data. Then, calculate the comprehensive comfort index from these indices and compare it with the environmental comfort threshold.

[0019] In this embodiment, it should be noted that the specific steps for obtaining the comprehensive comfort index are as follows: Acquire temperature data, including ambient air temperature, suitable temperature setpoint, temperature uniformity, ground temperature, radiation temperature, and heat source temperature. Evaluate the temperature comfort index based on the temperature data. Humidity data is acquired, including indoor humidity, target humidity setpoint, humidity gradient value for the current time period, ground humidity, air humidity and airflow, and the influence of local moisture sources. The humidity comfort index is then evaluated based on the humidity data. Acquire air quality data, including fine particulate matter concentration, carbon dioxide concentration, volatile organic compound concentration, and air circulation index, and evaluate the air comfort index based on the air quality data; Acquire light intensity data, including ambient light perception and target comfort. Illuminance value, uniformity of illumination distribution, and perception of natural light are used to evaluate the light comfort index based on illuminance intensity data. The temperature comfort index, humidity comfort index, air comfort index, and light comfort index are normalized. The normalized temperature comfort index, humidity comfort index, air comfort index, and light comfort index are then weighted and summed to calculate the comprehensive comfort index. The specific steps are as follows: ; In the formula To achieve a comprehensive comfort index, The normalized temperature comfort index, The normalized humidity comfort index. The air comfort index, The light comfort index. , , , These are the weighting coefficients for the normalized temperature comfort index, normalized humidity comfort index, normalized air comfort index, and normalized light comfort index. , , , The weighting coefficients are obtained through historical data analysis. This involves analyzing temperature, humidity, air quality, and light data over a specific period of time, extracting patterns from a large amount of historical data, and thus estimating these parameters. It should be noted that the historical data analysis method is an existing algorithm, a multi-indicator comprehensive evaluation method in weighted summation. This method can assign different weights to each indicator according to its importance in practical applications, thereby more flexibly and reasonably reflecting the differences in the contribution of each factor to the final result. Through weighted summation, the influence of key indicators can be highlighted in the comprehensive score, avoiding excessive interference from secondary factors in the overall judgment, and improving the accuracy and interpretability of the evaluation results.

[0020] In this embodiment, it should be noted that the specific steps for obtaining the temperature comfort index are as follows: Obtain the ambient air temperature and the suitable temperature setpoint from the temperature data, and calculate the temperature deviation coefficient by comparing the ratio of the ambient air temperature and the suitable temperature setpoint. Obtain the suitable temperature setpoint and temperature uniformity from the temperature data, and calculate the temperature uniformity coefficient by comparing the ratio of the suitable temperature setpoint and temperature uniformity in the temperature data. Obtain the temperature uniformity and ground temperature value from the temperature data, and calculate the ground temperature coefficient by comparing the temperature uniformity and ground temperature value. Obtain the ground temperature value and radiation temperature value from the temperature data, and calculate the radiation temperature coefficient by comparing the ground temperature value and radiation temperature value in the temperature data. Obtain the radiation temperature value and heat source temperature value from the temperature data, and then... The heat source temperature coefficient is obtained by calculating the ratio of the emitted temperature value to the heat source temperature value. Obtain the heat source temperature value and the suitable temperature set value from the temperature data, and calculate the heat source adjustment coefficient by comparing the ratio of the heat source temperature value and the suitable temperature set value in the temperature data. The temperature comfort index is calculated using the temperature deviation coefficient, temperature uniformity coefficient, ground temperature coefficient, radiation temperature coefficient, heat source temperature coefficient, and heat source adjustment coefficient. The specific steps are as follows: ; In the formula, For temperature comfort index, Heat source adjustment coefficient, The heat source temperature coefficient, This is the temperature deviation coefficient. This is the temperature uniformity coefficient. Ground temperature coefficient, The radiation temperature coefficient, , , These are the adjustment parameters for the heat source adjustment coefficient, temperature deviation coefficient, and ground temperature coefficient. , , The weighting coefficients are automatically learned and optimized through machine learning model algorithms. The model can automatically adjust the weighting coefficients based on environmental factors and corresponding comfort feedback in historical data, so as to achieve higher accuracy in future predictions. It should be noted that the machine learning model algorithm is an existing algorithm. The biggest advantage of the comprehensive temperature comfort calculation formula is that it can comprehensively integrate multiple environmental perception data to ensure the accurate adjustment of the temperature control system in complex environments.

[0021] In this embodiment, it should be noted that the specific steps for obtaining the humidity comfort index are as follows: obtain the indoor humidity value and the suitable humidity range from the humidity data, and calculate the humidity deviation coefficient by comparing the ratio of the indoor humidity value and the suitable humidity range from the humidity data. Obtain the target humidity setpoint and the tolerance of the target humidity setpoint from the humidity data, and calculate the humidity setting range coefficient by the ratio of the target humidity setpoint and the tolerance of the target humidity setpoint from the humidity data; Obtain the initial humidity value and the final humidity value for a historical period from the humidity data, and calculate the humidity change rate for the historical period by comparing the initial humidity value with the final humidity value. Obtain the humidity gradient value, humidity change rate, and historical humidity change rate from the humidity data for the current time period. Calculate the humidity fluctuation amplitude coefficient by combining these data. The specific steps are as follows: ; In the formula This is the humidity fluctuation amplitude coefficient. This represents the humidity gradient value within the current time period. This represents the rate of change in humidity over the current time period. The rate of change in humidity over a historical period; Obtain the difference between the ground humidity value and the ambient humidity value in the humidity data, and calculate the ground humidity deviation coefficient by comparing the difference between the ground humidity value and the ambient humidity value. Obtain air humidity, airflow velocity, and humidity stability from humidity data, and calculate the air humidity and airflow interaction coefficient by comparing the ratios of air humidity, airflow velocity, and humidity stability in the humidity data. The local humidity source influence and the intensity of the influence are obtained from the humidity data. The ratio of the local humidity source influence and the intensity of the influence is calculated to obtain the local humidity source comfort correction coefficient. The humidity deviation coefficient, humidity setting range coefficient, humidity fluctuation amplitude coefficient, ground humidity deviation coefficient, air humidity and airflow interaction coefficient, and local humidity source comfort correction coefficient are normalized. The normalized humidity deviation coefficient, humidity setting range coefficient, humidity fluctuation amplitude coefficient, ground humidity deviation coefficient, air humidity and airflow interaction coefficient, and local humidity source comfort correction coefficient are then used to calculate the humidity comfort index. The specific steps for obtaining this index are as follows: ; In the formula, Humidity comfort index, This is the humidity deviation coefficient. Set a range factor for humidity. This is the humidity fluctuation amplitude coefficient. This is the ground humidity deviation coefficient. This is the coefficient representing the interaction between air humidity and airflow. The local humidity source comfort correction coefficient uses multiplication and square root operations to make complex calculations more efficient, especially in data analysis problems. It can provide more accurate results and faster calculation speed, balance the contribution of six indicators, avoid a single indicator dominating the result, and quantify the overall credibility of the data.

[0022] In this embodiment, it should be noted that the specific steps for obtaining the air comfort index are as follows: Obtain the concentration of fine particulate matter and the air quality standard from the air quality data, and calculate the air quality index by the ratio of the fine particulate matter concentration to the air quality standard; Obtain the carbon dioxide concentration and carbon dioxide concentration threshold from the air quality data, and calculate the carbon dioxide impact index by comparing the carbon dioxide concentration and carbon dioxide concentration threshold in the air quality data. The concentration of volatile organic compounds (VOCs) and the VOC concentration threshold are obtained from the air quality data. The ratio of the VOC concentration in the air quality data to the VOC concentration threshold is calculated to obtain the VOC impact index. Obtain the air circulation index and standard circulation index from the air quality data, and calculate the air circulation impact index by comparing the air circulation index and standard circulation index in the air quality data. The air quality index, carbon dioxide impact index, organic compound impact index, and air circulation impact index are normalized. The air comfort index is then calculated from the normalized air quality index, carbon dioxide impact index, organic compound impact index, and air circulation impact index. The specific steps for obtaining this index are as follows: ; In the formula, The air comfort index, Air Quality Index. This is the carbon dioxide impact index. For the influence index of organic compounds, The harmonic mean formula is used to calculate the air circulation impact index. The harmonic mean avoids the situation where a certain maximum value in multiple data points excessively inflates the overall result. In practice, this helps to more realistically evaluate and optimize the system, without leading to unrealistic assessments due to insufficient data.

[0023] In this embodiment, it should be noted that the specific steps for obtaining the lighting comfort index are as follows: Obtain the ambient light perception and target light intensity values ​​from the light intensity data, and calculate the ambient light perception deviation index by comparing the ratio of the ambient light perception and target light intensity values ​​in the light intensity data. Obtain the target comfortable light value and the standard comfortable light range from the light intensity data, and calculate the light target compliance index by comparing the ratio of the target comfortable light value to the standard comfortable light range in the light intensity data. Obtain the uniformity of light distribution and the uniformity standard from the light intensity data, and calculate the light uniformity index by comparing the ratio of the uniformity of light distribution and the uniformity standard in the light intensity data. The natural light perception and preset natural light standard are obtained from the light intensity data, and the ratio of the light intensity data is calculated to obtain the natural light comfort index. The illumination perception deviation index, illumination target conformity index, illumination uniformity index, and natural illumination comfort index are normalized. The illumination comfort index is then calculated from these normalized indices. The specific steps are as follows: ; In the formula The light comfort index. This is the light perception deviation index. The target illumination compliance index. The light uniformity index. The Natural Light Comfort Index uses multiplication and square root operations to make complex calculations more efficient. Especially in data analysis problems, it can provide more accurate results and faster calculation speed, balance the contribution of the four indicators, avoid a single indicator dominating the result, and quantify the overall credibility of the data.

[0024] In this embodiment, it should be noted that the specific steps for determining whether temperature control adjustment is needed based on the comprehensive comfort index are as follows: The determination of whether temperature control adjustment is needed is based on the comprehensive comfort index. When the comprehensive comfort index is greater than or equal to the environmental comfort threshold, no adjustment is needed for indoor temperature control. When the comprehensive comfort index is less than the environmental comfort threshold, the indoor temperature control will be adjusted. It should be noted that the environmental comfort threshold is a standard value calculated by integrating multiple environmental perception data and combining existing technologies to determine whether the environment has reached a suitable comfort level.

[0025] Step 3: If it is determined that temperature control is needed, a machine learning model is used to dynamically monitor environmental changes and predict environmental change trends over a future period of time to obtain the environmental change trend.

[0026] In this embodiment, it should be noted that a machine learning model is used to dynamically monitor the environment. The changes, specifically the steps, are as follows: Machine learning models are a technology that automatically extracts patterns and makes predictions or decisions by analyzing and learning from historical data. In environmental comfort regulation systems, machine learning models can be trained using historical environmental data to learn trends and patterns of environmental changes. These models can predict future environmental data changes by identifying periodic, trend, and seasonal changes in time series. Machine learning models can effectively capture dependencies in long-term series and predict future temperature or humidity trends. They are suitable for short-term forecasting and trend analysis. By inputting these prediction results into the comfort index, the system can adjust thresholds or activate corresponding equipment in advance, thereby achieving rapid response and intelligent regulation to environmental changes. Through learning from historical environmental data, machine learning models can discover patterns and regularities in the data. Machine learning models train themselves to understand which factors lead to environmental changes and make predictions about future changes based on past data.

[0027] Step four: Based on environmental change trends and user comfort needs, combined with environmental comfort index and individual preference data, personalized temperature control adjustments are made.

[0028] In this embodiment, it should be noted that the steps for obtaining the user's comfort requirements are as follows: the user's comfort requirements include preferences for temperature, humidity, air quality, and lighting environment factors. These preference data are learned and optimized through environmental data recording and user feedback. In order to accurately obtain these requirements, the temperature control system adopts real-time feedback and machine learning algorithms to dynamically adjust the system settings in order to better meet the user's personalized needs.

[0029] In this embodiment, it should be noted that personalized temperature control is performed by combining environmental comfort index and individual preference data. The specific steps are as follows: The input information on temperature, humidity, light intensity, and air quality preferences is combined with a comprehensive comfort threshold based on real-time environmental data. Temperature control is then adjusted according to this comprehensive comfort threshold. This process improves the user experience and avoids the influence of a single standard on comfort adjustment.

[0030] In this embodiment, it should be noted that a temperature controller intelligent adjustment system based on multi-source environmental sensing includes: The data acquisition module is used to acquire temperature data, humidity data, air quality data, and light intensity data through temperature sensors, humidity sensors, air quality sensors, and light sensors. The data processing module is used to calculate the temperature comfort index, humidity comfort index, air comfort index, and light comfort index using temperature data, humidity data, air quality data, and light intensity data. It then calculates the comprehensive comfort index from these indices and determines whether temperature control adjustment is needed based on the comprehensive comfort index. The personalized demand analysis and adjustment module is used to dynamically monitor environmental changes through a machine learning model if it is determined that temperature control adjustment is needed, and to predict the environmental change trend over a period of time in the future. The optimization and feedback adjustment module is used to make personalized temperature control adjustments based on environmental change trends and user comfort needs, combined with environmental comfort index and individual preference data.

[0031] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0032] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for intelligent adjustment of a temperature controller based on multi-source environmental sensing, characterized in that, Includes the following steps: Step 1: Acquire temperature data, humidity data, air quality data, and light intensity data using temperature sensors, humidity sensors, air quality sensors, and light sensors. Step 2: Calculate the temperature comfort index, humidity comfort index, air comfort index, and light comfort index using temperature data, humidity data, air quality data, and light intensity data. Then, calculate the comprehensive comfort index from these indices. Based on the comprehensive comfort index, determine whether temperature control adjustment is currently necessary. Step 3: If it is determined that temperature control is needed, then a machine learning model is used to dynamically monitor environmental changes and predict the environmental change trend over a period of time in the future to obtain the environmental change trend. Step four: Based on environmental change trends and user comfort needs, combined with environmental comfort index and individual preference data, personalized temperature control adjustments are made.

2. The intelligent temperature controller adjustment method based on multi-source environmental sensing according to claim 1, characterized in that: The steps for obtaining the comprehensive comfort index are as follows: Acquire temperature data, including ambient air temperature, suitable temperature setpoint, temperature uniformity, ground temperature, radiation temperature, and heat source temperature. Evaluate the temperature comfort index based on the temperature data. Humidity data is acquired, including indoor humidity, target humidity setpoint, humidity gradient value for the current time period, ground humidity, air humidity and airflow, and the influence of local moisture sources. The humidity comfort index is then evaluated based on the humidity data. Acquire air quality data, including fine particulate matter concentration, carbon dioxide concentration, volatile organic compound concentration, and air circulation index, and evaluate the air comfort index based on the air quality data; Acquire light intensity data, including ambient light perception, target comfort light value, light distribution uniformity, and natural light perception. Evaluate the light comfort index based on the light intensity data. The temperature comfort index, humidity comfort index, air comfort index, and light comfort index are normalized, and then the normalized temperature comfort index, humidity comfort index, air comfort index, and light comfort index are weighted and summed to obtain the comprehensive comfort index.

3. The intelligent temperature controller adjustment method based on multi-source environmental sensing according to claim 1, characterized in that, The steps for obtaining the temperature comfort index are as follows: Obtain the ambient air temperature and the suitable temperature setpoint from the temperature data, and calculate the temperature deviation coefficient by comparing the ratio of the ambient air temperature and the suitable temperature setpoint. Obtain the suitable temperature setpoint and temperature uniformity from the temperature data, and calculate the temperature uniformity coefficient by comparing the ratio of the suitable temperature setpoint and temperature uniformity in the temperature data. Obtain the temperature uniformity and ground temperature value from the temperature data, and calculate the ground temperature coefficient by comparing the temperature uniformity and ground temperature value. Obtain the ground temperature value and radiation temperature value from the temperature data, and calculate the radiation temperature coefficient by comparing the ground temperature value and radiation temperature value in the temperature data. Obtain the radiation temperature value and heat source temperature value from the temperature data, and calculate the heat source temperature coefficient by comparing the ratio of the radiation temperature value and the heat source temperature value. Obtain the heat source temperature value and the suitable temperature set value from the temperature data, and calculate the heat source adjustment coefficient by comparing the ratio of the heat source temperature value and the suitable temperature set value in the temperature data. The temperature comfort index is calculated using the temperature deviation coefficient, temperature uniformity coefficient, ground temperature coefficient, radiation temperature coefficient, heat source temperature coefficient, and heat source adjustment coefficient.

4. The intelligent temperature controller adjustment method based on multi-source environmental sensing according to claim 1, characterized in that, The steps for obtaining the humidity comfort index are as follows: obtain the indoor humidity value and the suitable humidity range from the humidity data, and calculate the humidity deviation coefficient by comparing the indoor humidity value and the suitable humidity range from the humidity data. Obtain the target humidity setpoint and the tolerance of the target humidity setpoint from the humidity data, and calculate the humidity setting range coefficient by the ratio of the target humidity setpoint and the tolerance of the target humidity setpoint from the humidity data; Obtain the initial humidity value and the final humidity value for a historical period from the humidity data, and calculate the humidity change rate for the historical period by comparing the initial humidity value with the final humidity value. Obtain the humidity gradient value, humidity change rate, and historical humidity change rate from the humidity data for the current time period. Calculate the humidity fluctuation amplitude coefficient by combining these data. The specific steps are as follows: ； In the formula This is the humidity fluctuation amplitude coefficient. This represents the humidity gradient value within the current time period. This represents the rate of change in humidity over the current time period. The rate of change in humidity over a historical period; Obtain the difference between the ground humidity value and the ambient humidity value in the humidity data, and calculate the ground humidity deviation coefficient by comparing the difference between the ground humidity value and the ambient humidity value. Obtain air humidity, airflow velocity, and humidity stability from humidity data, and calculate the air humidity and airflow interaction coefficient by comparing the ratios of air humidity, airflow velocity, and humidity stability in the humidity data. The local humidity source influence and the intensity of the influence are obtained from the humidity data. The ratio of the local humidity source influence and the intensity of the influence is calculated to obtain the local humidity source comfort correction coefficient. The humidity deviation coefficient, humidity setting range coefficient, humidity fluctuation amplitude coefficient, ground humidity deviation coefficient, air humidity and airflow interaction coefficient, and local humidity source comfort correction coefficient are normalized. The humidity comfort index is then calculated by normalizing the humidity deviation coefficient, humidity setting range coefficient, humidity fluctuation amplitude coefficient, ground humidity deviation coefficient, air humidity and airflow interaction coefficient, and local humidity source comfort correction coefficient.

5. The intelligent temperature controller adjustment method based on multi-source environmental sensing according to claim 1, characterized in that: The steps for obtaining the air comfort index are as follows: Obtain the concentration of fine particulate matter and the air quality standard from the air quality data, and calculate the air quality index by the ratio of the fine particulate matter concentration to the air quality standard; Obtain the carbon dioxide concentration and carbon dioxide concentration threshold from the air quality data, and calculate the carbon dioxide impact index by comparing the carbon dioxide concentration and carbon dioxide concentration threshold in the air quality data. The concentration of volatile organic compounds (VOCs) and the VOC concentration threshold are obtained from the air quality data. The ratio of the VOC concentration in the air quality data to the VOC concentration threshold is calculated to obtain the VOC impact index. Obtain the air circulation index and standard circulation index from the air quality data, and calculate the air circulation impact index by comparing the air circulation index and standard circulation index in the air quality data. The air quality index, carbon dioxide impact index, organic compound impact index, and air circulation impact index are normalized, and the air comfort index is calculated from the normalized air quality index, carbon dioxide impact index, organic compound impact index, and air circulation impact index.

6. The intelligent temperature controller adjustment method based on multi-source environmental sensing according to claim 1, characterized in that: The steps for obtaining the lighting comfort index are as follows: Obtain the ambient light perception and target light intensity values ​​from the light intensity data, and calculate the ambient light perception deviation index by comparing the ratio of the ambient light perception and target light intensity values ​​in the light intensity data. Obtain the target comfortable light value and the standard comfortable light range from the light intensity data, and calculate the light target compliance index by comparing the ratio of the target comfortable light value to the standard comfortable light range in the light intensity data. Obtain the uniformity and uniformity standard of light distribution from the light intensity data, and then... The light uniformity index is calculated by comparing the uniformity of light distribution in the intensity data with the uniformity standard. The natural light perception and preset natural light standard are obtained from the light intensity data, and the ratio of the light intensity data is calculated to obtain the natural light comfort index. The illumination perception deviation index, illumination target conformity index, illumination uniformity index, and natural illumination comfort index are normalized. The illumination comfort index is then calculated from the normalized illumination perception deviation index, illumination target conformity index, illumination uniformity index, and natural illumination comfort index.

7. The intelligent temperature controller adjustment method based on multi-source environmental sensing according to claim 1, characterized in that: The steps for determining whether temperature control adjustment is needed based on the comprehensive comfort index are as follows: The overall comfort index is compared with the environmental comfort threshold. When the overall comfort index is greater than or equal to the environmental comfort threshold, the indoor temperature control does not need to be adjusted. When the overall comfort index is less than the environmental comfort threshold, the indoor temperature control will be adjusted.

8. A temperature controller intelligent adjustment system based on multi-source environmental sensing, used to implement the temperature controller intelligent adjustment method based on multi-source environmental sensing as described in any one of claims 1-7, characterized in that... The system includes: The data acquisition module is used to acquire temperature data, humidity data, air quality data, and light intensity data through temperature sensors, humidity sensors, air quality sensors, and light sensors. The data processing module is used to calculate the temperature comfort index, humidity comfort index, air comfort index, and light comfort index using temperature data, humidity data, air quality data, and light intensity data. It then calculates the comprehensive comfort index from these indices and determines whether temperature control adjustment is needed based on the comprehensive comfort index. The personalized demand analysis and adjustment module is used to dynamically monitor environmental changes through a machine learning model if it is determined that temperature control adjustment is needed, and to predict the environmental change trend over a period of time in the future. The optimization and feedback adjustment module is used to make personalized temperature control adjustments based on environmental change trends and user comfort needs, combined with environmental comfort index and individual preference data.

Images