Heat supply system power adjusting method and system based on big data

Through the big data fusion model and exponential moving average method, the power of the heating system is dynamically adjusted, which solves the problem that traditional heating systems cannot integrate multi-source data and insufficient adaptability, and achieves accurate energy consumption control and improved user comfort.

CN119063066AInactive Publication Date: 2024-12-03HEBEI XINGXIANG THERMAL POWER GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411570760.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-06
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional heating systems cannot effectively integrate multi-source data, resulting in the inability to achieve refined energy consumption control, lack of adaptive capabilities and self-learning mechanisms, and it is difficult to cope with complex indoor environment changes and user preferences, resulting in energy waste and management complexity.

Method used

Through the power adjustment method of heating system based on big data, the human body's body sense temperature is calculated using a multi-source data fusion model, combined with the exponential moving average method and the heating system running time, the indoor temperature is dynamically adjusted, and the optimal power output value of the heating system is calculated. , and precise control is achieved through the power adjustment execution module.

Benefits of technology

Significantly reduce energy waste, improve user comfort, achieve rapid response and smooth adjustment to temperature changes, and enhance the system's adaptability and energy use efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063066A_ABST
    Figure CN119063066A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of heat supply regulation, and particularly discloses a heat supply system power regulation method and system based on big data, and the method comprises the steps: obtaining an indoor environment temperature from a sensor network, and calculating a human body sensible temperature based on a multi-source data fusion model; calculating an indoor temperature dynamic adjustment coefficient according to the indoor environment temperature and the human body sensible temperature; according to the indoor temperature dynamic adjustment coefficient, an index moving average method is adopted, and the indoor temperature value is corrected in combination with the operation time of the heat supply system; on the basis of the corrected indoor temperature value, the volume of the heat supply room and historical energy consumption data, the power output optimal value of the heat supply system is calculated according to the current target set temperature, and the system power is adjusted to the optimal value; according to the method, more accurate temperature control can be realized, the comfort level of a user is improved, and energy waste is remarkably reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of heat supply regulation, and in particular relates to a power regulation method and system for a heat supply system based on big data. Background Art

[0002] Heating systems are indispensable in modern buildings. Traditional constant temperature control and simple switching strategies can no longer meet the increasingly complex heating needs. These systems usually rely on a single temperature sensor and a fixed temperature set point, ignoring the complexity of human thermal comfort, such as the influence of factors such as radiant temperature, humidity and air flow velocity. In addition, they often cannot adapt to the dynamic heat load changes of buildings, resulting in energy waste and indoor temperature fluctuations. In large buildings, this effect will be amplified, causing significant economic losses and environmental impacts.

[0003] With the development of Internet of Things technology and big data analysis, heating systems have the potential to achieve smarter and more precise control. However, current systems still have significant deficiencies in integrating and utilizing multi-source data. Although various sensors are deployed in buildings, these data are often isolated and fail to be effectively integrated to provide a comprehensive indoor environmental assessment. Existing control algorithms are usually based on simple proportional-integral-derivative (PID) control or preset rules, lacking in-depth consideration and predictive capabilities for complex environmental factors. This approach has difficulty coping with rapidly changing indoor conditions and external climate influences, and cannot fully utilize historical data to optimize long-term performance.

[0004] In addition, current heating systems generally lack flexibility and adaptability. They usually use rough step-by-step power regulation and cannot achieve refined energy consumption control. When faced with different user preferences, diverse spatial layouts, and changing usage patterns, these systems find it difficult to provide personalized solutions. At the same time, most systems lack effective self-learning mechanisms and cannot automatically optimize control strategies based on long-term operating data. This not only limits the continuous improvement of system efficiency, but also increases the complexity of management and maintenance. Against the backdrop of fluctuating energy prices and increasingly stringent environmental regulations, these limitations are becoming a major bottleneck in building energy management. Innovative solutions are urgently needed to break through the limitations of traditional heating systems and achieve smarter and more efficient heating management. Summary of the invention

[0005] The purpose of the present invention is to break through the limitations of the traditional heating system and achieve smarter and more efficient heating management. The specific technical solutions are as follows: In a first aspect, the present invention provides a power regulation method for a heating system based on big data, the method comprising the following steps: Step S1, obtaining the indoor ambient temperature from the sensor network, and calculating the human body temperature based on a multi-source data fusion model; Step S2, calculating the indoor temperature dynamic adjustment coefficient according to the indoor environment temperature and the human body temperature; Step S3, according to the indoor temperature dynamic adjustment coefficient, the indoor temperature value is corrected by using the exponential moving average method and combining the operation time of the heating system; Step S4, based on the corrected indoor temperature value, the volume of the heated room and the historical energy consumption data, the optimal power output value of the heating system is calculated according to the current target setting temperature, and the system power is adjusted to the optimal value.

[0006] Furthermore, the multi-source data fusion model is expressed as: ; In the formula, is the perceived temperature, is the mean radiation temperature, in degrees Celsius; is the water vapor partial pressure, is the atmospheric pressure, in hectopascals; is the indoor air velocity, is the outdoor air velocity in meters per second, is the volume of the heated room, For reference room volume, all units are cubic meters; and is the adjustable constant term of the model, where , .

[0007] Furthermore, in step S2, the indoor temperature dynamic adjustment coefficient is calculated The formula is: set up , which represents the difference between the human body temperature and the indoor ambient temperature. If the difference is positive, the heating needs to be reduced; if the difference is negative, the heating needs to be increased; The indoor temperature dynamic adjustment coefficient ,in, The nonlinear adjustment coefficient term has a value of 0.02; The heating system is set to calculate the indoor temperature dynamic adjustment coefficient every 15 to 30 minutes, and when Calculation is performed only when .

[0008] Furthermore, in step S3, the exponential moving average method is used to dynamically adjust the indoor temperature coefficient. Perform smoothing;

[0009] in, is the dynamic adjustment coefficient of indoor temperature after smoothing at the current moment, is the dynamic adjustment coefficient of indoor temperature after smoothing at the previous moment, is the dynamic adjustment coefficient of indoor temperature before smoothing at the current moment, , is the smoothing factor, the default value is 0.2.

[0010] The corrected indoor temperature value is The calculation is as follows:

[0011] in, The system running time in minutes.

[0012] Furthermore, the calculation formula for calculating the optimal power output value of the heating system according to the current target set temperature is:

[0013] In the formula, is the optimal power output value at the current moment, is the maximum value of the system power after adjustment in the previous three moments, Set a temperature for your target.

[0014] Further, in step S1, the sensor network includes a temperature sensor, a humidity sensor and an air flow velocity sensor, wherein: Temperature sensor is used to measure indoor ambient temperature and mean radiant temperature ; Humidity sensors are used to measure indoor relative humidity and calculate water vapor partial pressure ; Air velocity sensor is used to measure indoor air velocity .

[0015] Furthermore, the reference room volume The value is based on the average volume of all rooms in the heating system load.

[0016] Furthermore, the power regulation method further includes: setting upper and lower limit thresholds of power regulation and , the optimal power output value P satisfies: .

[0017] When the calculated power output is the optimal value When the threshold is exceeded, the system automatically Limits to the nearest threshold and alerts administrators.

[0018] According to the actual operation data, the upper and lower thresholds of power regulation are automatically adjusted to adapt to the changes in heating demand in different seasons and weather conditions.

[0019] In a second aspect, the present invention provides a heating system power regulation system based on big data, which is used to execute the method described in the first aspect, and the system includes a data acquisition module, a body temperature calculation module, a temperature adjustment coefficient calculation module, a temperature correction module, a power optimization module and a power regulation execution module connected in sequence.

[0020] The data acquisition module is used to obtain indoor environment temperature, humidity and air flow velocity data from the sensor network.

[0021] The body temperature calculation module is used to calculate the body temperature based on a multi-source data fusion model.

[0022] The temperature adjustment coefficient calculation module is used to calculate the indoor temperature dynamic adjustment coefficient according to the indoor ambient temperature and the human body temperature.

[0023] The temperature correction module is used to dynamically adjust the coefficient of indoor temperature, adopt the exponential moving average method and combine the operation time of the heating system to correct the indoor temperature value.

[0024] The power optimization module is used to calculate the optimal power output value of the heating system according to the current target set temperature based on the corrected indoor temperature value, the volume of the heated room and the historical energy consumption data.

[0025] The power regulation execution module is used to regulate the system power to the optimal value.

[0026] Furthermore, the system also includes: Threshold setting module, used to set the upper and lower thresholds of power regulation and .

[0027] Threshold limit module to ensure the calculated power output is at the optimal value satisfy: .

[0028] Alarm module for optimal power output When the threshold range is exceeded, P is automatically limited to the nearest threshold and an alert is issued to the administrator.

[0029] Compared with the prior art, the present invention has the following beneficial effects: The present invention calculates the human body temperature through a multi-source data fusion model, combined with the indoor ambient temperature, to achieve more accurate temperature control and improve user comfort. Based on the corrected indoor temperature value, room volume and historical energy consumption data, the optimal power output is calculated, which significantly reduces energy waste. The dynamic adjustment coefficient and exponential moving average method are used to achieve rapid response and smooth regulation to temperature changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a flow chart of the power regulation method of a heating system based on big data of the present invention.

[0031] Figure 2 It is a schematic diagram of the composition of the power regulation system of the heating system based on big data of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention is described clearly and completely below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Example 1: Figure 1 As shown, it is a flow chart of the power regulation method of the heating system based on big data of the present invention, and the method comprises the following steps: Step S1, obtaining the indoor ambient temperature from the sensor network, and calculating the human body temperature based on a multi-source data fusion model.

[0034] In step S1, the sensor network includes a temperature sensor, a humidity sensor and an air flow velocity sensor, wherein the temperature sensor is used to measure the indoor ambient temperature. and mean radiant temperature ; Humidity sensor is used to measure indoor relative humidity and calculate water vapor partial pressure ; Air velocity sensor is used to measure indoor air velocity .

[0035] The multi-source data fusion model is expressed as: ; In the formula, is the perceived temperature, is the mean radiation temperature, in degrees Celsius; is the water vapor partial pressure, is the atmospheric pressure, in hectopascals; is the indoor air velocity, is the outdoor air velocity in meters per second, is the volume of the heated room, For reference room volume, all units are cubic meters; and is the adjustable constant term of the model, where , .

[0036] Modern sensor technology and data fusion methods are used to overcome the limitations of traditional single temperature measurement. The multi-source data fusion model takes into account the main factors that affect human thermal perception, including ambient temperature, radiant temperature, humidity and airflow velocity, and also innovatively introduces room volume factors to adapt to different spatial characteristics.

[0037] Parameters in the model It reflects the influence of the average radiation temperature on the perceived temperature. Its value range is ( ) allows fine-tuning according to specific building characteristics, parameters ( ) takes into account the indirect effect of room volume on perceived temperature, which is particularly important in large or non-standard spaces; the water vapor partial pressure term ( ) reflects the effect of humidity on thermal comfort, while the air velocity term ( ) reflects the effect of airflow on reducing the perceived temperature.

[0038] Step S2, calculating the indoor temperature dynamic adjustment coefficient according to the indoor environment temperature and the human body temperature.

[0039] In step S2, the indoor temperature dynamic adjustment coefficient is calculated. The formula is: set up , which represents the difference between the human body temperature and the indoor ambient temperature. If the difference is positive, the heating needs to be reduced; if the difference is negative, the heating needs to be increased; The indoor temperature dynamic adjustment coefficient ,in, The nonlinear adjustment coefficient term has a value of 0.02. The introduction of the temperature dynamic adjustment coefficient is to achieve the dynamic response of the heating system to the temperature difference. The use of the tanh function ensures the smoothness of the adjustment and avoids sudden and large adjustments. The introduction of the nonlinear adjustment coefficient k further enhances the system's sensitivity to large temperature differences, allowing for stronger adjustments when the temperature difference is large.

[0040] The heating system is set to calculate the indoor temperature dynamic adjustment coefficient every 15 to 30 minutes, and when The calculation is performed only when the time comes. This design is to balance the system response speed and stability and avoid system fluctuations caused by frequent small adjustments.

[0041] Step S3, according to the indoor temperature dynamic adjustment coefficient, the indoor temperature value is corrected by using the exponential moving average method and combining the operation time of the heating system; In step S3, the exponential moving average method is used to dynamically adjust the indoor temperature coefficient Perform smoothing; ; in, is the dynamic adjustment coefficient of indoor temperature after smoothing at the current moment, is the dynamic adjustment coefficient of indoor temperature after smoothing at the previous moment, is the dynamic adjustment coefficient of indoor temperature before smoothing at the current moment, , is the smoothing factor, the default value is 0.2; this smoothing method can effectively filter short-term fluctuations while retaining long-term trends, making the system's response to environmental changes more stable. Smoothing factor The default value of 0.2 gives a moderate weight to new data, which ensures timely response of the system while avoiding over-sensitivity.

[0042] The corrected indoor temperature value is The calculation is as follows: ; in, The system running time in minutes.

[0043] Step S4, based on the corrected indoor temperature value, the volume of the heated room and the historical energy consumption data, the optimal power output value of the heating system is calculated according to the current target setting temperature, and the system power is adjusted to the optimal value.

[0044] The formula for calculating the optimal power output value of the heating system based on the current target set temperature is: ; In the formula, is the optimal power output value at the current moment, is the maximum value of the system power after adjustment in the previous three moments, Set a temperature for your target.

[0045] The reference room volume The value is based on the average volume of all rooms in the heating system load.

[0046] The power regulation method further includes: setting upper and lower thresholds of power regulation and , the optimal power output value P satisfies: .

[0047] When the calculated power output is the optimal value When the threshold is exceeded, the system automatically Limits to the nearest threshold and alerts administrators.

[0048] According to the actual operation data, the upper and lower thresholds of power regulation are automatically adjusted to adapt to the changes in heating demand in different seasons and weather conditions. For example, a large office building with 100 offices and an average volume of 200m³ was used to adjust the power of the heating system.

[0049] Initial setup: (target temperature) = 22°C; =50kW, =500kW; = 200m³ (average volume of all rooms).

[0050] On a cold winter morning, the outside temperature dropped to -5°C. The system started operating at 7:00am with an initial indoor temperature of 15°C.

[0051] The key data of the operation process are as follows: 7:00, the system starts, =15°C, ≈14°C (taking into account cold radiation); calculated =-1°C, S≈1.2; initial P is calculated to be 450kW (close to , to quickly heat up); 7:30, rise to 18°C, ≈17.4°C; =-0.6°C, S≈1.1, P is adjusted to 350kW; 8:00, reaches 20°C, ≈20°C; ≈0°C, S is not adjusted, P is further adjusted to 200kW; 8:30, Reaching 21.5°C, ≈21.8°C (considering the impact of people entering the office); =0.3°C,| |<0.5, no adjustment; 9:00, Maintain at 22°C, ≈22.2°C; the system enters a stable state, and P fluctuates slightly around 100kW.

[0052] During the whole process, the system dynamically adjusts the heating power according to the changes in indoor temperature and perceived temperature, achieving a fast and smooth heating process and maintaining a stable state after reaching the target temperature. At the same time, the system continuously monitors various parameters to prepare for possible temperature fluctuations or environmental changes; the system can effectively respond to large temperature changes and maintain stability after reaching the target temperature, reflecting its excellent dynamic adjustment capabilities and energy efficiency.

[0053] Example 2: Figure 2 As shown, this embodiment provides a power regulation system for a heating system based on big data. The system includes a data acquisition module, a body temperature calculation module, a temperature adjustment coefficient calculation module, a temperature correction module, a power optimization module and a power regulation execution module connected in sequence, which are used to execute the method described in Example 1.

[0054] The data acquisition module is used to obtain indoor environment temperature, humidity and air flow velocity data from the sensor network.

[0055] The body temperature calculation module is used to calculate the body temperature based on a multi-source data fusion model.

[0056] The temperature adjustment coefficient calculation module is used to calculate the indoor temperature dynamic adjustment coefficient according to the indoor ambient temperature and the human body temperature.

[0057] The temperature correction module is used to dynamically adjust the coefficient of indoor temperature, adopt the exponential moving average method and combine the operation time of the heating system to correct the indoor temperature value.

[0058] The power optimization module is used to calculate the optimal power output value of the heating system according to the current target set temperature based on the corrected indoor temperature value, the volume of the heated room and the historical energy consumption data.

[0059] The power regulation execution module is used to regulate the system power to the optimal value.

[0060] Furthermore, the system also includes: The threshold setting module is used to set the upper and lower thresholds P_min and P_max of power regulation.

[0061] The threshold limiting module is used to ensure that the calculated optimal power output value P satisfies: P_min≤P≤P_max.

[0062] The alarm module is used for automatically limiting P to a nearest threshold value when the optimal value P of power output exceeds a threshold range, and sending an alarm to an administrator.

[0063] These modules work closely together to form an intelligent, efficient and safe closed-loop control system. The system can not only accurately control heating power and optimize energy efficiency, but also has the ability to self-protect and report abnormalities. Through continuous data collection and analysis, the system can also continuously optimize itself and adapt to changes in heating demand in different seasons and weather conditions.

[0064] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power regulation method for a heating system based on big data, characterized in that: The method comprises the following steps: Step S1, obtaining the indoor ambient temperature from the sensor network, and calculating the human body temperature based on a multi-source data fusion model; Step S2, calculating the indoor temperature dynamic adjustment coefficient according to the indoor environment temperature and the human body temperature; Step S3, according to the indoor temperature dynamic adjustment coefficient, the indoor temperature value is corrected by using the exponential moving average method and combining the operation time of the heating system; Step S4, based on the corrected indoor temperature value, the volume of the heated room and the historical energy consumption data, the optimal power output value of the heating system is calculated according to the current target setting temperature, and the system power is adjusted to the optimal value.

2. The method for regulating the power of a heating system based on big data according to claim 1, characterized in that: The multi-source data fusion model is expressed as: ; In the formula, is the perceived temperature, is the mean radiation temperature, in degrees Celsius; is the water vapor partial pressure, is the atmospheric pressure, in hectopascals; is the indoor air velocity, is the outdoor air velocity in meters per second, is the volume of the heated room, For reference room volume, all units are cubic meters; and is the adjustable constant term of the model, where , .

3. The method for regulating the power of a heating system based on big data according to claim 2 is characterized in that: In step S2, the indoor temperature dynamic adjustment coefficient is calculated. The formula is: set up , which represents the difference between the human body temperature and the indoor ambient temperature. If the difference is positive, the heating needs to be reduced; if the difference is negative, the heating needs to be increased; The indoor temperature dynamic adjustment coefficient ,in, The nonlinear adjustment coefficient term has a value of 0.02; The heating system is set to calculate the indoor temperature dynamic adjustment coefficient every 15 to 30 minutes, and when Calculation is performed only when .

4. The method for regulating the power of a heating system based on big data according to claim 3 is characterized in that: In step S3, the exponential moving average method is used to dynamically adjust the indoor temperature coefficient Perform smoothing; ; in, is the dynamic adjustment coefficient of indoor temperature after smoothing at the current moment, is the dynamic adjustment coefficient of indoor temperature after smoothing at the previous moment, is the dynamic adjustment coefficient of indoor temperature before smoothing at the current moment, , is the smoothing factor, the default value is 0.2; The corrected indoor temperature value is The calculation is as follows: ; in, The system running time in minutes.

5. The method for regulating the power of a heating system based on big data according to claim 4 is characterized in that: The formula for calculating the optimal power output value of the heating system based on the current target set temperature is: ; In the formula, is the optimal power output value at the current moment, is the maximum value of the system power after adjustment in the previous three moments, Set a temperature for your target.

6. The method for regulating the power of a heating system based on big data according to claim 5, characterized in that: In step S1, the sensor network includes a temperature sensor, a humidity sensor and an air flow velocity sensor, wherein: Temperature sensor is used to measure indoor ambient temperature and mean radiant temperature ; Humidity sensors are used to measure indoor relative humidity and calculate water vapor partial pressure ; Air velocity sensor is used to measure indoor air velocity .

7. The method for regulating the power of a heating system based on big data according to claim 6, characterized in that: The reference room volume The value is based on the average volume of all rooms in the heating system load.

8. The method for regulating power of a heating system based on big data according to any one of claims 1 to 7, characterized in that: The power regulation method further includes: setting upper and lower thresholds of power regulation and , the optimal power output value P satisfies: ; When the calculated power output is the optimal value When the threshold is exceeded, the system automatically Limit to the nearest threshold and send an alert to the administrator; According to the actual operation data, the upper and lower thresholds of power regulation are automatically adjusted to adapt to the changes in heating demand in different seasons and weather conditions.

9. A heating system power regulation system based on big data, used to execute the method according to any one of claims 1 to 8, characterized in that: The system comprises: Data acquisition module, used to obtain indoor environment temperature, humidity, and air flow speed data from the sensor network; The body temperature calculation module is used to calculate the body temperature based on the multi-source data fusion model; The temperature adjustment coefficient calculation module is used to calculate the indoor temperature dynamic adjustment coefficient according to the indoor environment temperature and the human body temperature; A temperature correction module is used to adjust the indoor temperature value according to the indoor temperature dynamic adjustment coefficient, using the exponential moving average method and combining the operation time of the heating system; A power optimization module for calculating the optimal power output of the heating system according to the current target set temperature based on the corrected indoor temperature value, the volume of the heated room and the historical energy consumption data; The power regulation execution module is used to regulate the system power to the optimal value.

10. The power regulation system for a heating system based on big data according to claim 9, characterized in that: The system further comprises: Threshold setting module, used to set the upper and lower thresholds of power regulation and ; Threshold limit module to ensure the calculated power output is at the optimal value satisfy: ; Alarm module for optimal power output When the threshold range is exceeded, P is automatically limited to the nearest threshold and an alert is issued to the administrator.