Building energy consumption precise regulation system and method based on multi-factor dynamic correlation and nonlinear modeling

Abstract

The application discloses a building energy consumption precise regulation and control system and method based on multi-factor dynamic correlation and nonlinear modeling, belongs to the technical field of energy consumption regulation and control, and comprises a data acquisition module, which is used for acquiring relevant data of a target building, the relevant data comprising air conditioner power consumption and lighting, and generating a database corresponding to the target building according to the relevant data; and a data processing module, which is responsive to the database and is used for processing the relevant data in the database, the data processing module comprising a distinguishing unit and a feature extraction unit. Through technical means such as refined sub-metering, dynamic correlation of environmental and personnel factors, nonlinear heat load modeling and multi-monitoring-point temperature transmission analysis, the application realizes precise prediction and dynamic regulation and control of building energy consumption, and significantly improves energy-saving efficiency.

Description

Technical Field

[0001] This invention relates to the field of energy consumption control technology, and in particular to a building energy consumption precision control system and method based on multi-factor dynamic correlation and nonlinear modeling. Background Technology

[0002] With the continuous improvement of building scale and function, building energy consumption has become a very high and important component of total energy consumption. Especially in large public buildings, complexes, and smart parks, building operation involves multiple types of energy equipment such as HVAC systems, lighting systems, and fresh air systems, and their operating status is affected by a combination of factors such as external climate conditions, building structural characteristics, and user behavior.

[0003] Regarding this research, application CN202511208592.0 provides a BIM-based building energy consumption optimization method. This technical solution includes acquiring and preprocessing the raw data of the target building, mapping the preprocessed raw data onto a BIM model to obtain a dynamic BIM data model, and constructing a five-dimensional spatiotemporal feature tensor. The five-dimensional spatiotemporal feature tensor is then subjected to dimensionality reduction and compression transformation, and based on the compressed three-dimensional tensor, a disturbance response function is constructed. This technical solution addresses the problems of traditional building energy consumption optimization methods in building energy management, such as difficulty in spatiotemporal fusion of multi-source data, difficulty in accurately modeling dynamic coupling relationships, and lack of real-time adaptability of control vectors.

[0004] Another application, CN202211660715.0, provides a method, system, terminal, and medium for optimizing building energy consumption control. This technical solution includes acquiring power output fluctuation data of generator sets and power load fluctuation data of target buildings; determining the upper and lower limits of power load for the target buildings at corresponding target times; determining the scheduling optimization interval for the target buildings at corresponding times; establishing a control optimization model with the goal of minimizing the sum of the control optimization values ​​of all target buildings; and solving for the energy consumption control strategies for each target building. This technical solution can achieve a balanced distribution of energy consumption among buildings while meeting the demand intensity of each building with relatively small errors.

[0005] However, the above technical solutions can only handle single-variable predictions. Energy consumption is affected by multiple factors such as weather, personnel density, and equipment status. The above technical solutions failed to achieve optimized linkage, resulting in a low amount of energy consumption reduction after the implementation of energy-saving strategies, which is difficult to meet the needs of quantitative management. Summary of the Invention

[0006] In view of the problems existing in the field of energy consumption control technology, the present invention is proposed.

[0007] Therefore, one of the objectives of this invention is to provide a building energy consumption precision control system and method based on multi-factor dynamic correlation and nonlinear modeling. Through refined sub-item metering, dynamic correlation of environmental and human factors, nonlinear heat load modeling, and multi-monitoring point temperature transfer analysis, it achieves precise prediction and dynamic control of building energy consumption, significantly improving energy efficiency.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] On the one hand, this invention provides a building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling, comprising:

[0010] The data acquisition module is used to acquire relevant data of the target building, including air conditioning power consumption and lighting, and to generate a database corresponding to the target building based on the relevant data.

[0011] A data processing module, which responds to the database and processes relevant data within the database, includes a differentiation unit and a feature extraction unit.

[0012] The differentiation unit is used to differentiate between high power consumption and lighting, medium power consumption and lighting, and low power consumption and lighting in the database, and to obtain the correlation factors with the high power consumption and lighting. The correlation factors include the weather temperature of the area where the target building is located and the population density inside the target building.

[0013] The feature extraction unit responds to the personnel density and is used to extract the impact of personnel density on air conditioning power consumption in the target area within the target building.

[0014] The data fusion processing module includes a monitoring unit, an acquisition unit, a calculation unit, and a control unit.

[0015] The monitoring unit, based on the population density and area of ​​the target area, is used to monitor temperature changes in the target area. The monitoring method includes setting [a specific location within the target area]. , ,..., Monitoring point For the set number One monitoring point;

[0016] The acquisition unit responds to the set monitoring points to acquire the distance between each monitoring point and the air conditioner, and gives at least 5 to 6 feature monitoring points based on the distance. The method of giving the distance includes giving one unit distance for each distance from the air conditioner, and the unit distance includes 7 to 10 meters.

[0017] The calculation unit is used to perform related calculations, including calculating the temperature transfer changes within the target area under the condition of the unit distance.

[0018] In a preferred embodiment of the present invention, the control unit responds to the temperature transmission change and is used to preset a critical threshold for the transmission change. The critical threshold is the temperature transmission efficiency between adjacent feature monitoring points, and the transmission efficiency is whether the temperature increase between adjacent feature monitoring points exceeds 1°C within a duration of 20 to 30 seconds.

[0019] If the transmission change is lower than the critical threshold, the system determines that the transmission efficiency between adjacent feature monitoring points is low and increases the temperature of the air conditioner; otherwise, no determination is made.

[0020] In a preferred embodiment of the present invention, the feature extraction unit extracts the impact of personnel density on air conditioning power consumption in the target area within the target building. The extraction steps are as follows:

[0021] The target building is divided into sub-regions, and each sub-region is treated as an independent analysis unit.

[0022] Count the number of people per unit area in each of the independent analysis units;

[0023] Remove outliers;

[0024] The data was smoothed using a sliding window averaging method with a window length of 5 minutes. The data was the number of people per unit area after removing outliers.

[0025] Synchronize the data with the air conditioner power consumption using timestamps, with a time resolution of 1 minute.

[0026] Quantify the linear correlation between the number of people per unit area and the power of air conditioners;

[0027] Calculate the change in the number of people per unit area and the air conditioning response delay time;

[0028] The number of people per unit area is divided into three levels: low, medium, and high. The low level is <0.2 people / ㎡, the medium level is 0.2 to 0.5 people / ㎡, and the high level is >0.5 people / ㎡.

[0029] A linear model was fitted to the number of people per unit area in the three categories of low, medium and high, and the slope was extracted as a sensitivity index.

[0030] For the area corresponding to the high-end, quadratic regression was used to collect the nonlinear growth trend of the heat load in the area when people gather;

[0031] The regions will be compared with those corresponding to low-end, mid-end, and high-end, and the comparison will include quantifying the degree of influence of the spatial layout of each region on the situation.

[0032] In a preferred embodiment of the present invention, the calculation unit calculates the temperature transfer change within the target area over the unit distance, based on the following formula:

[0033] ;

[0034] In the formula, The heat flux density represents the amount of heat passing through a unit area within the target region.

[0035] The thermal conductivity of the material reflects the thermal insulation performance of the wall / partition within the target area.

[0036] This represents the cross-sectional area perpendicular to the direction of heat flow.

[0037] This indicates the temperature difference, which is the temperature difference between the air outlet of the air conditioner and each monitoring point.

[0038] This represents the heat transfer distance, which corresponds to the unit distance.

[0039] In a preferred embodiment of the present invention, the following formula is also included:

[0040] ;

[0041] In the formula, Indicates convective heat transfer. Indicates the convective heat transfer coefficient;

[0042] Indicates the heat exchange surface area. Indicates air temperature. This indicates the temperature at the monitoring point.

[0043] As a preferred embodiment of the present invention, the feature is that, based on the calculation results, at least three horizontally distributed verification points are set between adjacent feature monitoring points in each given feature monitoring point, and temperature detection is performed at each verification point. When the system determines that the transmission efficiency between adjacent feature monitoring points is low, if the temperature of any verification point between the adjacent feature monitoring points increases by more than 1°C, the system does not determine that the transmission efficiency between adjacent feature monitoring points is low.

[0044] In a preferred embodiment of the present invention, the linear correlation between the number of people per unit area and the power of the air conditioner is quantified and calculated according to the following formula:

[0045] ;

[0046] In the formula, The Pearson correlation coefficient is used to measure the linear correlation between population density and air conditioning power, and is dimensionless from -1 to 1.

[0047] This represents the total number of data samples. Indicates the first Personnel density at a given time point;

[0048] Indicates the first The power of the air conditioner at a specific point in time;

[0049] The time series mean of population density This represents the time series mean of the air conditioner's power.

[0050] In a preferred embodiment of the present invention, the slope is extracted as a sensitivity index and calculated according to the following formula:

[0051] ;

[0052] In the formula, The slope represents the linear regression slope, indicating the change in air conditioning power when the population density increases by 1 unit.

[0053] Indicates the total number of data samples;

[0054] Indicates the first Population density at each time point; (independent variable)

[0055] Indicates the first Air conditioner power at each time point (dependent variable)

[0056] This represents the sum of the products of population density and air conditioner power (cross term).

[0057] This represents the sum of time series data representing population density.

[0058] The sum of the time series power of the air conditioner;

[0059] This represents the sum of squares of population density.

[0060] In a preferred embodiment of the present invention, the following calculation is performed: For the area corresponding to the high-end location, quadratic regression is used to collect data on the nonlinear increase in heat load during periods of high population density, and the result is obtained according to the following formula:

[0061] ;

[0062] In the formula, This indicates the air conditioner's power consumption at a population density of [missing information]. The predicted value at that time Indicates population density;

[0063] This represents the threshold separating the linear phase from the exponential phase.

[0064] Represents the slope of the linear phase;

[0065] Represents the intercept of the linear phase;

[0066] Indicates the initial value of the exponential phase;

[0067] Indicates the growth rate during the exponential phase;

[0068] This represents the final value adjustment term during the exponential phase.

[0069] On the other hand, the present invention provides a method for applying to the building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling as described above, comprising the following steps:

[0070] Acquire relevant data about the target building, including air conditioning power consumption and lighting, and generate a database corresponding to the target building based on the relevant data;

[0071] The database is used to distinguish between high power consumption and lighting, medium power consumption and lighting, and low power consumption and lighting. The correlation factors with high power consumption and lighting are obtained. The correlation factors include the weather temperature of the area where the target building is located and the population density inside the target building.

[0072] The impact of personnel density on air conditioning power consumption was extracted in the target area within the target building.

[0073] Monitoring temperature changes in the target area, the monitoring method includes setting within the target area... , ,..., Monitoring point For the set number One monitoring point;

[0074] Obtain the distance between each monitoring point and the air conditioner, and assign at least 5 to 6 characteristic monitoring points based on the distance. The assignment method includes assigning a unit distance to the air conditioner for each unit distance, where the unit distance includes 7 to 10 meters.

[0075] Perform relevant calculations, including calculating the temperature transfer changes within the target area at the unit distance.

[0076] Beneficial effects:

[0077] 1. This invention generates a database of target buildings through a data acquisition module, covering detailed data such as air conditioning power consumption and lighting. This avoids the extensive "total distribution" model in traditional energy consumption statistics and can accurately locate high-energy-consuming areas. This provides a data foundation for subsequent regulation. For example, after distinguishing between high / medium / low power consumption areas, equipment operation strategies can be optimized in a targeted manner.

[0078] 2. By linking weather temperature, population density, and high power consumption areas, the system quantifies the impact of population density on air conditioning power consumption, achieving "on-demand control." For example, when population density increases from low to high, the system automatically increases the air conditioning heating capacity.

[0079] 3. For areas with high population density, a quadratic regression model is used to capture the nonlinear growth of heat load, solve the problem of underestimating energy consumption in dense scenes, avoid equipment overload, and increase heating capacity in advance when people gather through nonlinear prediction to prevent air conditioning from shutting down due to sudden increase in load.

[0080] 4. By setting monitoring points in the target area, the system calculates the temperature transfer change per unit distance and avoids local overheating by setting a critical threshold for transfer efficiency. For example, if the monitoring finds that the temperature transfer efficiency in a certain area is low (such as an area directly blew by an air conditioner), the system can reduce the wind speed in that area to prevent energy waste. Furthermore, by verifying the temperature at the monitoring points (with three horizontally distributed points between adjacent monitoring points), the system corrects the uneven temperature caused by spatial layout (such as partitions and furniture). Attached Figure Description

[0081] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of the modular structure of the building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling, according to an embodiment of the present invention. Figure 2This is a schematic diagram of the method flow according to an embodiment of the present invention; The numbers in the diagram are: 110 - Data acquisition module; 120 - Data processing module; 1201 - Differentiation unit; 1202 - Feature extraction unit; 130 - Data fusion processing module; 1301 - Monitoring unit; 1302 - Acquisition unit; 1303 - Calculation unit; 1304 - Control unit. Detailed Implementation

[0082] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0083] Because the technical solution can only handle single-variable predictions and is difficult to achieve optimized linkage, the amount of energy consumption reduction after the implementation of energy-saving strategies is too low and cannot meet the needs of quantitative management.

[0084] Based on this, the present invention proposes a building energy consumption precision control system and method based on multi-factor dynamic correlation and nonlinear modeling. Through refined sub-item metering, dynamic correlation of environmental and human factors, nonlinear heat load modeling and multi-monitoring point temperature transfer analysis, it realizes precise prediction and dynamic control of building energy consumption, and significantly improves energy efficiency.

[0085] The present solution will be further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0086] Reference Figures 1 to 2 This is one embodiment of the present invention, which provides a building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling, comprising:

[0087] The data acquisition module 110 is used to acquire relevant data of the target building, including air conditioning power consumption and lighting, and generate a database corresponding to the target building based on the relevant data.

[0088] In this embodiment, data such as air conditioning power consumption and lighting energy consumption of the target building are acquired through sensors or interfaces, and a corresponding database is generated.

[0089] It provides high-precision raw data for subsequent itemized measurement and dynamic control, avoiding errors caused by traditional "total statistics";

[0090] The data processing module 120 responds to the database and is used to process relevant data in the database. The data processing module 120 includes a differentiation unit 1201 and a feature extraction unit 1202.

[0091] The differentiation unit 1201 is used to differentiate between high power consumption and lighting, medium power consumption and lighting, and low power consumption and lighting in the database, and to obtain the correlation factors with high power consumption and lighting. The correlation factors include the weather temperature of the area where the target building is located and the population density in the target building.

[0092] In this embodiment, high, medium and low power consumption areas are distinguished in the database and associated with external factors such as weather temperature and personnel density, which can quickly identify areas with abnormal energy consumption (such as continuous high energy consumption of nighttime lighting on a certain floor) and reduce invalid inspections.

[0093] Feature extraction unit 1202 responds to personnel density and is used to extract the impact of personnel density on air conditioning power consumption in a target area within a target building. The extraction steps are as follows:

[0094] The target building is divided into sub-areas (such as office areas, meeting rooms, and corridors), and each sub-area is treated as an independent analysis unit.

[0095] The number of people per unit area (persons / ㎡) in each independent analysis unit is counted, including through infrared array sensors or cameras;

[0096] Remove outliers (such as a sudden surge in the number of people due to sensor malfunction);

[0097] The data was smoothed using a sliding window averaging method, with a window length of 5 minutes. The data consisted of the number of people per unit area after removing outliers.

[0098] Synchronize the data with the air conditioner power consumption by timestamp, with a time resolution of 1 minute;

[0099] Quantify the linear correlation between the number of people per unit area and the power of air conditioners;

[0100] Calculate the change in the number of people per unit area and the delay time of the air conditioning response (such as the delay in the air conditioning power increase after people enter).

[0101] The number of people per unit area is divided into three levels: low, medium, and high. The low level is <0.2 people / ㎡, the medium level is 0.2 to 0.5 people / ㎡, and the high level is >0.5 people / ㎡.

[0102] A linear model was fitted to the number of people per unit area in the three categories of low, medium and high, and the slope was extracted as a sensitivity index.

[0103] For areas corresponding to high-end properties, quadratic regression was used to collect data on the nonlinear growth trend of heat load when people gather.

[0104] The comparison will be made with areas corresponding to low-end, mid-end, and high-end, including quantifying the impact of the spatial layout of each area on the situation.

[0105] In this embodiment, the impact of personnel density on air conditioning power consumption is quantified, and the steps include sub-region division, data smoothing, and linear regression.

[0106] The data fusion processing module 130 includes a monitoring unit 1301, an acquisition unit 1302, a calculation unit 1303, and a control unit 1304.

[0107] Monitoring unit 1301 monitors temperature changes in the target area based on population density and area. The monitoring method includes setting parameters within the target area. , ,..., Monitoring point For the set number One monitoring point;

[0108] The acquisition unit 1302 responds to the set monitoring points to acquire the distance between each monitoring point and the air conditioner, and gives at least 5 to 6 characteristic monitoring points based on the distance. The way the distance is given includes giving one unit distance per unit distance from the air conditioner, and the unit distance includes 7 to 10 meters.

[0109] Monitoring points are set up in the target area, and temperature changes are monitored based on population density and area. Temperature sensors are arranged at intervals of 7 to 10 meters to form a grid monitoring network.

[0110] For example, if the temperature in a corner area is found to be 2°C higher than in the center, local ventilation needs to be strengthened;

[0111] By combining personnel density data, determine whether the temperature anomaly is caused by the gathering of people (such as a sudden rise in temperature after the meeting has started).

[0112] The calculation unit 1303 is used to perform related calculations, including calculating the temperature transfer changes within the target area over a unit distance; the calculations are based on the following formula:

[0113] ;

[0114] In the formula, Heat flux density (W / m²) represents the amount of heat passing through a unit area within a target region.

[0115] It represents the thermal conductivity of the material (W / (m·K)), which reflects the thermal insulation performance of the wall / partition within the target area;

[0116] Represents the cross-sectional area perpendicular to the direction of heat flow; (m²);

[0117] This indicates the temperature difference, which is the temperature difference between the air conditioner's outlet and each monitoring point.

[0118] This represents the distance (m) that heat flow is transferred, and the corresponding unit distance is the distance that heat flow is transferred.

[0119] In this embodiment, the rate at which heat from the air conditioner is conducted to the monitoring point through the wall or air is calculated, for example, the temperature attenuation at 10m from the air outlet is analyzed.

[0120] It also includes calculations based on the following formula:

[0121] ;

[0122] In the formula, This represents convective heat transfer (W). This represents the convective heat transfer coefficient (W / (m²·K)), which is related to air velocity and surface roughness.

[0123] This represents the heat exchange surface area (m²). Indicates air temperature. This indicates the temperature at the monitoring point;

[0124] In this embodiment, the convective heat transfer between the air supply of the air conditioner and the surface of indoor objects (such as furniture and human bodies) is calculated, for example, the magnitude of the increase in local temperature caused by the increase in personnel density is analyzed;

[0125] The control unit 1304 responds to the temperature transmission change and is used to preset a critical threshold for the transmission change. The critical threshold is the temperature transmission efficiency between adjacent feature monitoring points. The transmission efficiency is whether the temperature increase between adjacent feature monitoring points exceeds 1°C within a duration of 20 to 30 seconds.

[0126] If the transmission change is below the critical threshold, the system determines that the transmission efficiency between adjacent feature monitoring points is low and increases the temperature of the air conditioner; otherwise, it does not make a determination.

[0127] In this embodiment, the air conditioning temperature is dynamically adjusted according to the critical threshold of temperature transfer efficiency (temperature difference between adjacent monitoring points > 1°C within 20-30 seconds). If the transfer efficiency is low (e.g., in a partitioned area), the target temperature of the air conditioning is increased by 1°C; otherwise, the current setting is maintained. This can prevent abnormal temperature operation of the air conditioning due to local partitions, and the energy saving rate reaches 8%-12%.

[0128] Based on the calculation results, at least three horizontally distributed verification points are set between adjacent feature monitoring points in each given feature monitoring point. Temperature detection is performed at each verification point. When the system determines that the transmission efficiency between adjacent feature monitoring points is low, if the temperature of any verification point between adjacent feature monitoring points increases by more than 1°C, the system will not determine that the transmission efficiency between adjacent feature monitoring points is low.

[0129] In this case, the system determines that the transmission efficiency between adjacent feature monitoring points is normal;

[0130] The linear correlation between the number of people per unit area and the power of air conditioners is quantified and calculated using the following formula:

[0131] ;

[0132] In the formula, The Pearson correlation coefficient is used to measure the linear correlation between population density and air conditioning power, and is dimensionless from -1 to 1.

[0133] This represents the total number of data samples (time series length). Indicates the first Personnel density at a given time point;

[0134] Indicates the first The power consumption (instantaneous power consumption) of the air conditioner at a specific point in time;

[0135] The time series mean of population density This represents the time series mean of the air conditioner's power.

[0136] The slope is extracted as a sensitivity index and calculated according to the following formula:

[0137] ;

[0138] In the formula, The slope of the linear regression (sensitivity index) represents the change in air conditioning power when the population density increases by 1 unit.

[0139] Indicates the total number of data samples (the length of the time series at the current level);

[0140] Indicates the first Personnel density at each time point (independent variable);

[0141] Indicates the first The power of the air conditioner at each time point (dependent variable);

[0142] This represents the sum of the products of population density and air conditioner power (cross term).

[0143] This represents the sum of time series data representing population density.

[0144] The sum of the time series power of the air conditioner;

[0145] This represents the sum of squares of personnel density (used to eliminate the influence of dimensions).

[0146] For areas corresponding to high-end properties, quadratic regression was used to collect data on the nonlinear growth of heat load during periods of high population density. The results were calculated using the following formula:

[0147] ;

[0148] In the formula, This indicates the air conditioner's power consumption at a population density of [missing information]. The predicted value at that time Indicates population density; (independent variable);

[0149] This represents the threshold separating the linear and exponential phases (the critical point for population density).

[0150] Indicates the slope of the linear phase (low density sensitivity).

[0151] Represents the intercept (base power) in the linear phase.

[0152] This represents the initial value of the exponential phase (the power offset at the critical point).

[0153] It represents the growth rate during the exponential phase (high-density sensitivity), and is dimensionless.

[0154] This represents the final value adjustment term during the exponential phase (to avoid infinite growth).

[0155] As can be seen from the above, this application achieves accurate prediction and dynamic control of building energy consumption through technical means such as refined sub-item metering, dynamic correlation of environmental and human factors, nonlinear heat load modeling, and temperature transfer analysis at multiple monitoring points, thereby significantly improving energy efficiency.

[0156] This embodiment, in conjunction with the aforementioned building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling, also proposes the system's working method, as follows:

[0157] S10: Obtain relevant data for the target building, including air conditioning power consumption and lighting, and generate a database corresponding to the target building based on the relevant data;

[0158] S20: In the database, distinguish between high power consumption and lighting, medium power consumption and lighting, and low power consumption and lighting, and obtain the correlation factors with high power consumption and lighting. The correlation factors include the weather temperature of the area where the target building is located and the population density in the target building.

[0159] S30: Extract the impact of personnel density on air conditioning power consumption in the target area within the target building;

[0160] S40: Monitor temperature changes in the target area. The monitoring method includes setting a temperature range within the target area. , ,..., Monitoring point For the set number One monitoring point;

[0161] S50: Obtain the distance between each monitoring point and the air conditioner, and provide at least 5 to 6 characteristic monitoring points based on the distance. The method of providing the distance includes providing one unit distance per unit distance from the air conditioner, and the unit distance includes 7 to 10 meters.

[0162] S60: Perform relevant calculations, including calculating the temperature transfer changes within the target area per unit distance.

[0163] In summary, by employing refined sub-metering, dynamic correlation of environmental and human factors, nonlinear heat load modeling, and multi-monitoring point temperature transfer analysis, we have achieved accurate prediction and dynamic control of building energy consumption, significantly improving energy efficiency (expected to reduce air conditioning energy consumption by 10% to 20%) and spatial comfort (reducing temperature unevenness by more than 50%). This technology is widely applicable to civil and commercial building scenarios of different sizes.

[0164] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling, characterized in that, include: The data acquisition module is used to acquire relevant data of the target building, including air conditioning power consumption and lighting, and to generate a database corresponding to the target building based on the relevant data. A data processing module, which responds to the database and processes relevant data within the database, includes a differentiation unit and a feature extraction unit. The differentiation unit is used to differentiate between high power consumption and lighting, medium power consumption and lighting, and low power consumption and lighting in the database, and to obtain the correlation factors with the high power consumption and lighting. The correlation factors include the weather temperature of the area where the target building is located and the population density inside the target building. The feature extraction unit responds to the personnel density and is used to extract the impact of personnel density on air conditioning power consumption in a target area within the target building. The extraction steps are as follows: The target building is divided into sub-regions, and each sub-region is treated as an independent analysis unit. Count the number of people per unit area in each of the independent analysis units; Remove outliers; The data was smoothed using a sliding window averaging method with a window length of 5 minutes. The data was the number of people per unit area after removing outliers. Synchronize the data with the air conditioner power consumption using timestamps, with a time resolution of 1 minute. Quantify the linear correlation between the number of people per unit area and the power of air conditioners; Calculate the change in the number of people per unit area and the air conditioning response delay time; The number of people per unit area is divided into three levels: low, medium, and high. The low level is <0.2 people / ㎡, the medium level is 0.2 to 0.5 people / ㎡, and the high level is >0.5 people / ㎡. A linear model was fitted to the number of people per unit area in the three categories of low, medium and high, and the slope was extracted as a sensitivity index. For the sub-regions corresponding to high-end areas, quadratic regression was used to collect the nonlinear growth trend of heat load in the sub-regions when people gather; In the target area, it will be compared with the sub-areas corresponding to low-end, mid-end and high-end, and the comparison includes quantifying the degree of influence of the spatial layout of each sub-area on the trend; The data fusion processing module includes a monitoring unit, an acquisition unit, a calculation unit, and a control unit. The monitoring unit, based on the population density and area of ​​the target area, is used to monitor temperature changes in the target area. The monitoring method includes setting [a specific location within the target area]. , ,..., Monitoring point For the set number One monitoring point; The acquisition unit responds to the set monitoring points to acquire the distance between each monitoring point and the air conditioner, and gives at least 5 to 6 feature monitoring points based on the distance. The method of giving the distance includes giving one unit distance for each distance from the air conditioner, and the unit distance includes 7 to 10 meters. The calculation unit is used to perform related calculations, including calculating the temperature transfer changes within the target area under the condition of the unit distance; The control unit responds to temperature transmission changes and is used to preset a critical threshold for the transmission change. The critical threshold is the temperature transmission efficiency between adjacent feature monitoring points. The transmission efficiency is whether the temperature increase between adjacent feature monitoring points exceeds 1°C within a duration of 20 to 30 seconds. If the transmission change is lower than the critical threshold, the system determines that the transmission efficiency between adjacent feature monitoring points is low and increases the power of the air conditioner; otherwise, it does not increase the power.

2. The building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling as described in claim 1, characterized in that, In the calculation unit, the temperature transfer change within the target area under the given unit distance is calculated according to the following formula: ； In the formula, The heat flux density represents the amount of heat passing through a unit area within the target region. The thermal conductivity of the material reflects the thermal insulation performance of the wall / partition within the target area. This represents the cross-sectional area perpendicular to the direction of heat flow. This indicates the temperature difference, which is the temperature difference between the air outlet of the air conditioner and each monitoring point. This represents the heat transfer distance, which corresponds to the unit distance.

3. The building energy consumption precision control system and method based on multi-factor dynamic correlation and nonlinear modeling as described in claim 2, characterized in that, It also includes calculations based on the following formula: ； In the formula, Indicates convective heat transfer. Indicates the convective heat transfer coefficient; Indicates the heat exchange surface area. Indicates air temperature. This indicates the temperature at the monitoring point.

4. The building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling as described in any one of claims 2 to 3, characterized in that, Based on the calculation results, at least three horizontally distributed verification points are set between adjacent feature monitoring points in each given feature monitoring point. Temperature detection is performed at each verification point. When the system determines that the transmission efficiency between adjacent feature monitoring points is low, if the temperature of any verification point between the adjacent feature monitoring points increases by more than 1°C, the system does not determine that the transmission efficiency between adjacent feature monitoring points is low.

5. The building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling as described in claim 1, characterized in that, The linear correlation between the number of people per unit area and the power of air conditioners is quantified and calculated using the following formula: ； In the formula, The Pearson correlation coefficient is used to measure the linear correlation between population density and air conditioning power, and is dimensionless from -1 to 1. This represents the total number of data samples. Indicates the first Personnel density at a given time point; Indicates the first The power of the air conditioner at a specific point in time; The time series mean of population density This represents the time series mean of the air conditioner's power.

6. The building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling as described in claim 1, characterized in that, The slope is extracted as a sensitivity index and calculated according to the following formula: ； In the formula, The slope represents the linear regression slope, indicating the change in air conditioning power when the population density increases by 1 unit. Indicates the total number of data samples; Indicates the first Personnel density at a given time point; Indicates the first The power of the air conditioner at a specific point in time; This represents the sum of the products of population density and air conditioner power. This represents the sum of time series data representing population density. The sum of the time series power of the air conditioner; This represents the sum of squares of population density.

7. The building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling as described in claim 1, characterized in that, For the sub-regions corresponding to high-end areas, quadratic regression was used to collect the nonlinear growth trend of heat load in these sub-regions during periods of high population density, and the results were calculated using the following formula: ； In the formula, This indicates the air conditioner's power consumption at a population density of [missing information]. The predicted value at that time Indicates population density; This represents the threshold separating the linear phase from the exponential phase. Indicates the slope of the linear phase, low density sensitivity; Represents the intercept of the linear phase; Indicates the initial value of the exponential phase; It represents the growth rate during the exponential phase, exhibits high-density sensitivity, and is dimensionless. This represents the final value adjustment term during the exponential phase.

8. A method applied to the building energy consumption precision control system based on multi-factor dynamic correlation and nonlinear modeling as described in claim 1, characterized in that, Includes the following steps: Acquire relevant data about the target building, including air conditioning power consumption and lighting, and generate a database corresponding to the target building based on the relevant data; The database is used to distinguish between high power consumption and lighting, medium power consumption and lighting, and low power consumption and lighting. The correlation factors with high power consumption and lighting are obtained. The correlation factors include the weather temperature of the area where the target building is located and the population density inside the target building. The impact of population density on air conditioning power consumption is extracted in a target area within the target building. The extraction steps are as follows: The target building is divided into sub-regions, and each sub-region is treated as an independent analysis unit. Count the number of people per unit area in each of the independent analysis units; Remove outliers; The data was smoothed using a sliding window averaging method with a window length of 5 minutes. The data was the number of people per unit area after removing outliers. Synchronize the data with the air conditioner power consumption using timestamps, with a time resolution of 1 minute. Quantify the linear correlation between the number of people per unit area and the power of air conditioners; Calculate the change in the number of people per unit area and the air conditioning response delay time; The number of people per unit area is divided into three levels: low, medium, and high. The low level is <0.2 people / ㎡, the medium level is 0.2 to 0.5 people / ㎡, and the high level is >0.5 people / ㎡. A linear model was fitted to the number of people per unit area in the three categories of low, medium and high, and the slope was extracted as a sensitivity index. For the sub-regions corresponding to high-end areas, quadratic regression was used to collect the nonlinear growth trend of heat load in the sub-regions when people gather; In the target area, it will be compared with the sub-areas corresponding to low-end, mid-end and high-end, and the comparison includes quantifying the degree of influence of the spatial layout of each sub-area on the trend; Monitoring temperature changes in the target area, the monitoring method includes setting within the target area... , ,..., Monitoring point For the set number One monitoring point; Obtain the distance between each monitoring point and the air conditioner, and assign at least 5 to 6 characteristic monitoring points based on the distance. The assignment method includes assigning a unit distance to the air conditioner for each unit distance, where the unit distance includes 7 to 10 meters. Perform relevant calculations, including calculating the temperature transfer changes within the target area under the condition of the unit distance; A preset critical threshold for the transmitted change is defined as the temperature transmission efficiency between adjacent feature monitoring points. The transmission efficiency is defined as whether the temperature increase between adjacent feature monitoring points exceeds 1°C within a duration of 20 to 30 seconds. If the transmission change is lower than the critical threshold, the system determines that the transmission efficiency between adjacent feature monitoring points is low and increases the power of the air conditioner; otherwise, it does not increase the power.

Images