Building carbon hub adaptive ai control system

Abstract

The present application relates to the field of artificial intelligence technology, specifically to a building carbon nerve center adaptive AI control system, the system comprises a carbon perception analysis module, an optimization strategy calculation module, a structure energy efficiency mapping module, a space-time matching screening module and a regulation and control fusion module.In the present application, by perceiving the building environment and equipment state, the energy consumption density and carbon emission path data are extracted, the energy flow and carbon flow continuity are analyzed, the high energy consumption area and low efficiency area are accurately calibrated, the optimization is provided with quantitative basis, the area recognition accuracy is improved, the energy efficiency difference significant section is demarcated, through space-time joint screening, the relevance of carbon emission index and environmental parameters is strengthened, the stable performance area is identified, the adaptability and sustainability of the optimization path are improved, the building as a whole is promoted to develop in the direction of energy saving, low carbon and high efficiency, the continuous optimization in the dynamic environment is realized, the energy use efficiency and carbon emission control response rate are improved, and the intelligentialization and foresight of building operation and maintenance are enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence technology, in particular to a building carbon neural center adaptive AI control system. BACKGROUND

[0002] The field of building technology includes research and application of technologies related to building energy management, carbon emission control, air conditioning system energy efficiency optimization, etc. With the increasing global attention on carbon emission reduction targets, how to efficiently reduce building energy consumption and carbon emissions has become a technical problem to be solved. Traditional building energy consumption management technologies have problems such as long data update cycle, inaccurate energy efficiency evaluation, low system efficiency, etc. Especially in the operation of air conditioning systems and carbon emission measurement, there are difficulties in precise monitoring and control. In addition, the operation and maintenance cost of buildings is generally high, with a large amount of funds invested in passive maintenance, making it difficult to achieve a dynamic and preventive management mode. The core content of building energy efficiency management includes environmental perception, device monitoring, system optimization, etc. The goal is to improve the overall energy efficiency of buildings, reduce carbon emissions, optimize resource allocation, and improve the sustainability of building operation.

[0003] Among them, the building carbon neural center adaptive AI control system refers to a building energy efficiency optimization system combining intelligent decision-making and carbon flow control. The system uses device-level monitoring, system-level optimization, and city-level linkage technology to accurately improve the energy efficiency of air conditioning and high-energy-consuming devices in buildings and track carbon emissions. The system uses multi-dimensional data collection and real-time analysis methods to monitor multiple indicators such as building internal environment, energy consumption, and carbon emissions, ensuring that each device and system operates at the best energy efficiency and carbon efficiency. Through precise monitoring of each device in the building, energy consumption data is analyzed and automatic optimization decisions are made to achieve the goal of reducing building energy consumption and carbon emissions.

[0004] Traditional technologies rely on periodic data collection and static evaluation, which cannot reflect energy consumption fluctuations and real-time carbon emission behavior during building operation, resulting in lagging control decisions and insensitive responses. The data update cycle is long, and it is difficult to perceive and analyze the running state of high-frequency devices in detail, making it difficult to locate abnormal energy consumption areas. In energy efficiency evaluation, it relies on coarse-grained energy consumption indicators, ignoring the influence of building internal space structure on energy efficiency, and the evaluation results are difficult to guide specific adjustment behavior. Especially in the operation and management of air conditioning and high-energy-consuming devices, the monitoring granularity is too coarse, lacking a dynamic matching mechanism in time and space dimensions, causing energy consumption optimization decisions to be distorted, making it difficult to adapt to multi-scenario operation requirements. Carbon emission monitoring is mostly estimated, lacking continuous tracking of carbon flow paths, and unable to effectively analyze the spatio-temporal characteristics of carbon emissions in buildings. Building operation and maintenance still rely on passive maintenance, lacking a real-time data-based early warning mechanism, resulting in slow fault response, increasing maintenance costs, and affecting the continuity and economy of building operation. SUMMARY

[0005] The object of the present application is to solve the shortcomings existing in the prior art, and the building carbon nerve center adaptive AI control system is proposed.

[0006] In order to achieve the above object, the technical scheme adopted by the present application is as follows: the building carbon nerve center adaptive AI control system comprises:

[0007] The energy-carbon sensing analysis module obtains building environment and equipment operation state information, extracts energy consumption distribution density and carbon emission dynamic path, marks high energy consumption areas and low efficiency areas in the building by comparing the energy flow direction of the region and the continuity of the carbon flow, and generates an energy-carbon sensitive map;

[0008] The optimization strategy calculation module calls the energy-carbon sensitive map, divides the equipment operation detail block, identifies the energy consumption difference rate and the carbon emission boundary offset, selects the region meeting the threshold value as the optimization coverage unit, performs energy-carbon bidirectional mapping comparison, and generates an optimization mapping correlation group;

[0009] The structure energy efficiency mapping module extracts the building space structure level corresponding to the equipment operation carbon flow direction offset according to the optimization mapping correlation group, judges the energy efficiency change section, delimits the activity area and the reference area, and obtains a building structure energy efficiency hierarchical table;

[0010] The space-time matching screening module calls the building structure energy efficiency hierarchical table, selects the building operation unit scale range, identifies the multi-period carbon emission style area, compares the coincidence proportion of temperature and humidity consistency and energy consumption frequency difference, screens the optimal matching style area, and generates a space-time corresponding relationship list.

[0011] As a further scheme of the present application, the energy-carbon sensitive map comprises energy flow main direction distribution density, carbon flow continuity level identification, regional efficiency label, and energy consumption response feature map, the optimization mapping correlation group comprises optimization coverage region number, energy consumption difference comparison item, carbon emission boundary offset record, and mapping corresponding index table, the building structure energy efficiency hierarchical table comprises structure level number, carbon flow direction mapping relationship, energy efficiency change section label, structure stability parameter, and active area positioning marker, and the space-time corresponding relationship list comprises scale matching range set, style domain selection list, energy consumption frequency coincidence coefficient, and temperature and humidity feature overlap rate index.

[0012] As a further scheme of the present application, the energy-carbon sensing analysis module comprises:

[0013] The energy consumption mapping extraction submodule obtains building environment and equipment operation state information, extracts temperature gradient values and humidity channel offset values in the corresponding region, compares the average amplitude of the temperature gradient values and the standard deviation of the humidity channel offset values in the region, and generates an energy consumption migration tendency value;

[0014] The structure continuous evaluation sub-module identifies a building area humidity gradient change rate and a carbon flow communication segment length based on the energy consumption migration tendency value, compares a density distribution of the humidity gradient change rate with a variation interval of the communication segment length, and obtains a structure compatibility distribution coefficient;

[0015] The sensitive area calibration sub-module extracts a carbon flow overflow rate and a direction consistency value in the building according to the structure compatibility distribution coefficient, screens a regional aggregated distribution of the carbon flow overflow rate and the direction consistency value, calibrates a high energy consumption area and a low efficiency area, and generates an energy carbon sensitive map.

[0016] As a further scheme of the present application, the optimization strategy calculation module comprises:

[0017] The map division sub-module calls the energy carbon sensitive map, extracts a building structure block and an energy carbon clustering area, extracts a humidity offset degree and a carbon emission gradient, performs morphological aggregation and block division on a local area, and performs equipment operation structure division to generate an optimization detail block partition;

[0018] The energy consumption identification sub-module calls the optimization detail block partition, extracts a partition energy consumption frequency distribution and carbon emission boundary data, identifies a humidity change rate and a boundary displacement rate, screens according to an energy consumption difference threshold and a carbon emission boundary change determination standard, and obtains an energy consumption mapping area set;

[0019] The mapping generation sub-module extracts a building environment feature and an equipment operation feature according to the energy consumption mapping area set, compares a humidity distribution vector and a carbon emission response tensor in the area, calculates an optimization intensity value between areas, performs feature mapping index combination as a basis, and generates an optimization mapping association group.

[0020] As a further scheme of the present application, the structure energy efficiency mapping module comprises:

[0021] The structure layer extraction sub-module extracts an arrangement matrix of a space area and an energy flow direction graph in the building according to the optimization mapping association group, identifies a carbon flow direction offset vector in equipment operation, compares a distribution change amount of both at the same space position, arranges building areas according to a gradient difference, and generates an optimization guide space hierarchy graph.

[0022] The active area identification sub-module extracts a regional carbon flow density graph and a carbon flow direction offset graph according to the optimization guide space hierarchy graph, judges a local density gradient section, screens a high fluctuation segment area according to an offset amplitude difference value, calculates a regional high fluctuation value, labels a corresponding position as a high energy consumption structure area or a low efficiency structure area, and obtains a building structure energy efficiency layered table.

[0023] As a further scheme of the present application, the space-time matching screening module comprises:

[0024] The structure scale calibration sub-module calls the building structure energy efficiency hierarchical table, extracts the hierarchical distribution of high-frequency carbon flow areas and low-frequency stable areas in the building, divides the structure unit boundary according to the temperature and humidity response intensity gradient value, and generates a structure unit scale interval;

[0025] The style domain analysis sub-module extracts the temperature and humidity histogram amplitude under the differential period based on the structure unit scale interval, detects the carbon flow symbiotic matrix change rate between adjacent periods, and establishes a multi-period style domain set;

[0026] The style matching degree calculation sub-module calls the multi-period style domain set, calculates the spatio-temporal correspondence matching degree value, compares the coincidence proportion threshold of each style domain, and generates a spatio-temporal correspondence list.

[0027] As a further scheme of the present application, the system further comprises a regulation fusion module:

[0028] The regulation fusion module calls the spatio-temporal correspondence list, and in the regulation process, the temperature and humidity balance, carbon emission response and energy consumption intensity of each unit building block are counted, combined with environmental and equipment weight cross analysis, the energy consumption reservation threshold and carbon emission activation factor are set, and the building energy and carbon emission regulation framework is generated;

[0029] The building energy and carbon emission regulation framework comprises a temperature and humidity balance layer, a carbon emission response distribution graph, an energy consumption intensity adjustment factor, and an energy consumption reservation weight setting table.

[0030] As a further scheme of the present application, the regulation fusion module comprises:

[0031] The temperature and humidity balance sub-module extracts the temperature and humidity channel value of the building block, calls the spatio-temporal correspondence list to determine the area scale level, compares the temperature and humidity distribution of the building block according to the level temperature and humidity reference value, adjusts the channel value deviating from the reference, and obtains the temperature and humidity distribution weight;

[0032] The carbon emission identification sub-module extracts the carbon emission gradient value and the temperature and humidity difference value of the building block based on the temperature and humidity distribution weight, screens the carbon emission key area, and identifies by comparing the response intensity and the gradient difference ratio of the adjacent area, to obtain a carbon emission continuity measurement graph;

[0033] The energy-carbon fusion sub-module calls the carbon emission continuity measurement graph and the energy consumption intensity value and environmental priority value of each building block, combines the energy consumption reservation threshold and the carbon emission activation factor, and performs regulation distribution on the building block according to the area scale, to generate a building energy and carbon emission regulation framework.

[0034] Compared with the prior art, the present application has the advantages and positive effects that:

[0035] In the present application, by sensing the building environment and equipment state, the energy consumption density and carbon emission path data are extracted, and the energy flow and carbon flow continuity are analyzed, so that the high energy consumption area and low efficiency area can be clearly marked, providing quantitative basis for subsequent optimization. By comparing the differentiated energy consumption and carbon emission indicators, the building area is identified in fine granularity, effectively solving the ambiguity of traditional methods in energy consumption boundary judgment, improving the accuracy of regional identification, and by establishing the mapping relationship between building space structure and equipment operation state, combined with the change of carbon flow direction, the energy efficiency difference significant section is marked, forming a quantifiable space energy efficiency hierarchy. The joint screening of time period and space is introduced to strengthen the correlation between carbon emission pattern and environmental parameters, identify stable performance areas in changing building operation scenarios, and improve the adaptability and sustainability of the optimization path. By constructing multi-dimensional analysis relationship, superimposing environmental and equipment operation factors, the building block level energy consumption threshold setting and carbon emission control factor activation are realized, promoting the overall operation to the direction of energy saving, low carbon and high efficiency, and the processing logic forms a closed loop from perception, analysis, structure mapping, space-time identification to comprehensive control, each link is supported by data-driven accurate decision-making, realizing continuous optimization in dynamic operation environment, breaking the limitations of traditional static control, effectively improving the building energy use efficiency and carbon emission control response rate, and enhancing the intelligence and foresight of building operation and maintenance. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 The system flowchart of the present application is shown in Figure 1.

[0037] Figure 2 The flowchart of the energy and carbon perception and analysis module in the present application is shown in Figure 2.

[0038] Figure 3 The flowchart of the optimization strategy calculation module in the present application is shown in Figure 3.

[0039] Figure 4 The flowchart of the structure energy efficiency mapping module in the present application is shown in Figure 4.

[0040] Figure 5 The flowchart of the space-time matching and screening module in the present application is shown in Figure 5.

[0041] Figure 6 The flowchart of the control fusion module in the present application is shown in Figure 6. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical scheme and advantages of the present application more clear and explicit, the present application is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0043] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0044] Please refer to Figure 1 The building carbon nerve center adaptive AI control system comprises:

[0045] The energy and carbon sensing analysis module obtains building environment and equipment operation state information, extracts energy consumption distribution density and carbon emission dynamic path, and marks high energy consumption areas and low efficiency areas in the building by comparing the energy flow direction of the region and the continuity of the carbon flow, to generate an energy and carbon sensitive map;

[0046] The optimization strategy calculation module calls the energy and carbon sensitive map, divides the equipment operation detail block, identifies the energy consumption difference rate and the carbon emission boundary offset, selects the region meeting the threshold value as the optimization coverage unit, and performs energy and carbon bidirectional mapping comparison to generate an optimization mapping association group;

[0047] The structure energy efficiency mapping module extracts the building space structure hierarchy corresponding to the equipment operation carbon flow direction offset according to the optimization mapping association group, judges the energy efficiency change section, and delimits the activity area and the reference area to obtain a building structure energy efficiency hierarchical table;

[0048] The space-time matching screening module calls the building structure energy efficiency hierarchical table, selects the building operation unit scale range, identifies the multi-period carbon emission style area, compares the coincidence proportion of temperature and humidity consistency and energy consumption frequency difference, screens the optimal matching style area, and generates a space-time correspondence relationship list;

[0049] The regulation and control fusion module calls the space-time correspondence relationship list, and in the regulation and control process, it counts the temperature and humidity balance, carbon emission response and energy consumption intensity of each unit building block, combines with the environmental and equipment weight cross analysis, sets the energy consumption reservation threshold and the carbon emission activation factor, and generates a building energy and carbon emission regulation and control framework.

[0050] The energy-carbon sensitivity map includes energy flow main direction distribution density, carbon flow continuity level identification, regional efficiency label, and energy consumption response characteristic map. The optimization mapping correlation group includes optimization coverage area number, energy consumption difference control item, carbon emission boundary offset record, and mapping corresponding index table. The building structure energy efficiency layering table includes structure level number, carbon flow direction mapping relationship, energy efficiency change section label, structure stability parameter, and active area positioning marker. The space-time corresponding relationship list includes scale matching range set, style domain selection list, energy consumption frequency coincidence coefficient, and temperature and humidity characteristic overlap rate index. The building energy and carbon emission regulation framework includes temperature and humidity balance layer, carbon emission response distribution map, energy consumption intensity adjustment factor, and energy consumption reservation weight setting table.

[0051] Please refer to Figure 2 The energy-carbon sensing analysis module includes:

[0052] The energy consumption mapping extraction sub-module obtains building environment and equipment operation state information, extracts temperature gradient values and humidity channel offset values in the corresponding area, compares the average amplitude of the temperature gradient values and the standard deviation of the humidity channel offset values in the area, and generates an energy consumption migration tendency value.

[0053] The access installs the temperature and humidity sensors in each area of the building and the equipment operation state monitoring system, and receives the temperature and humidity data of each room and public area in the building and the on-off state, running power and other information of air conditioning, lighting, ventilation and other equipment in real time. For the central air conditioning system of an office building, the temperature sensor data of all rooms are collected every 5 minutes, for example, the temperature of room A is 22.5℃, the temperature of room B is 23.1℃, and the temperature of room C is 21.8℃, and the outdoor temperature is 15℃. The temperature difference between adjacent rooms or different positions in the same room is calculated, for example, the temperature difference between the window area and the center area of room A is 0.8℃, and the temperature gradient value of this area is recorded as 0.8℃ / m. The average amplitude of the temperature gradient value of all areas in the building is calculated, for example, the average amplitude of the temperature gradient value of all areas in the building is 0.5℃ / m. The humidity data of each area is obtained from the humidity sensor, for example, the humidity of room A is 55%RH, the humidity of room B is 58%RH, and the humidity of room C is 53%RH. The humidity distribution unevenness caused by air flow or equipment operation is analyzed and quantified as a humidity channel offset value, for example, the humidity near the ventilation port of room A is offset by 3%RH compared with the average humidity, and the humidity channel offset value of this area is recorded as 3%RH. The humidity channel offset values of all areas are counted and the standard deviation of the offset values is calculated, for example, the standard deviation of the humidity channel offset values of all areas in the building is 2%RH. The average amplitude of the temperature gradient value 0.5℃ / m and the standard deviation of the humidity channel offset value 2%RH are compared. By comparison, if the standard deviation of the humidity channel offset value is greater than the average amplitude of the temperature gradient value, it is considered that energy is more likely to migrate through the humidity channel, otherwise it is through the temperature gradient. According to the comparison result, the energy consumption migration tendency value is given, for example, in this sampling, the standard deviation of the humidity channel offset is large, so the energy consumption migration tendency value is biased to the humidity migration, and the energy consumption migration tendency value data for subsequent analysis is generated.

[0054] The structure continuous evaluation submodule identifies the temperature and humidity gradient change rate and energy flow density in the building area based on the energy consumption migration tendency value, compares the density distribution of the temperature and humidity gradient change rate with the variation interval of the energy flow density, and obtains the structure compatibility distribution coefficient.

[0055] Receiving the energy consumption migration tendency value (for example, biasing the humidity migration), and combining the CAD drawing or BIM model of the building, identifying the temperature and humidity gradient change rate of each region inside the building. For the temperature gradient change rate, a number of temperature monitoring points can be selected in a continuous distribution, and the temperature difference between adjacent monitoring points is calculated. For example, in a 10-meter-long corridor, 5 temperature sensors are evenly arranged, and the measured temperatures at a certain time are 22℃, 22.2℃, 22.5℃, 22.8℃, and 23℃. The temperature gradient in the first section is (22.2-22) / 2=0.1℃ / m, the second section is (22.5-22.2) / 2=0.15℃ / m, and the change rate is (0.15-0.1) / 2=0.025℃ / m². The humidity gradient change rate can be calculated in the same way. Combined with the building structure information, the path and length of the energy flow continuous transmission are analyzed, for example, the straight-line distance from the air supply outlet to the air return outlet of a room is 5 meters, and there is an energy flow transmission path with a length of 5 meters in this area. The lengths of all such energy flow paths in the building are counted and their distribution is analyzed, and the numerical statistics of the temperature and humidity gradient change rates are obtained, and the density distribution histogram is drawn. For example, the temperature gradient change rate is mainly distributed in the 0-0.05℃ / m² interval, and the humidity gradient change rate is mainly distributed in the 0-0.03%RH / m² interval. Combined with the distribution interval of the energy flow path length (such as the path length mainly distributed between 2 meters and 8 meters), the density distribution of the temperature and humidity gradient change rates is compared with the variation interval of the energy flow path length. If the regions with high gradient change rates and long energy flow paths are consistent in spatial distribution, it is considered that the building structure has high compatibility for energy consumption migration, and a high structure compatibility distribution coefficient is given. For example, when the area with a gradient change rate greater than 0.03℃ / m² and an energy flow path length greater than 5 meters accounts for more than 60% of the total area, the structure compatibility distribution coefficient can be set to 0.8, which serves as the basis for subsequent sensitive area calibration.

[0056] The sensitive area calibration sub-module extracts the carbon flow overflow rate and direction consistency value in the building according to the structure compatibility distribution coefficient, filters the regional aggregation distribution of the carbon flow overflow rate and direction consistency value, calibrates the high energy consumption area and low efficiency area, and generates an energy-carbon sensitive map.

[0057] The receiving structure compatible distribution coefficient (for example, 0.8) is combined with the carbon emission monitoring data inside the building to extract the carbon flow overflow rate of each area in the building. Specifically, the energy flow is converted by the emission factor to form the corresponding carbon flow index, and the carbon flow overflow rate is calculated by analyzing the inflow and outflow of the energy flow in the area. For example, the carbon flow of an office in a certain period of time is 0.9 kg, and the carbon emission generated by the local public power grid emission factor is 1 kg, so the carbon flow overflow rate is 0.9 / 1=0.9. The consistency of the carbon flow direction is calculated, for example, in a certain office area, the consistency of the energy flow direction monitored by the sensor is high, which is quantified as the direction consistency value 0.85. For the area with a carbon flow overflow rate greater than 0.8 and a direction consistency value greater than 0.75, a density-based spatial clustering algorithm (DBSCAN) is used to cluster the areas that meet the conditions. For example, several adjacent office areas are aggregated into a high energy consumption area cluster. For the area aggregated, it is sorted according to its energy consumption intensity (for example, unit area energy consumption), and the area with high energy consumption intensity is selected as the high energy consumption area. For example, the area with unit area energy consumption greater than 30 W / m² is marked as a high energy consumption area. Further analyze the area with high carbon flow overflow rate (for example, greater than 1) and poor direction consistency (for example, less than 0.6), and mark it as an inefficient area, which appears in the area with low energy utilization efficiency, such as some ventilation dead angle or equipment aging area. The marked high energy consumption area and inefficient area are visualized on the building plan to generate an energy-carbon sensitive map, which highlights the high energy consumption area and inefficient area with different colors or marks, and is used to guide the subsequent optimization strategy formulation.

[0058] Please refer to Figure 3 The optimization strategy calculation module includes:

[0059] The map division sub-module calls the energy-carbon sensitive map, extracts the building structure block and the energy-carbon clustering area, extracts the temperature and humidity offset degree and the carbon emission gradient, performs morphological aggregation and blocking on the local area, and performs device operation structure division to generate an optimization detail block partition;

[0060] The energy carbon sensitive map is called, which marks the high energy consumption areas and low efficiency areas in the building with different colors, for example, red represents high energy consumption areas A and B, blue represents low efficiency areas C and D, and green represents normal areas E and F. The information of building structural blocks such as load-bearing walls, columns, floors, etc. is extracted from the BIM model of the building, as well as the energy carbon cluster areas A, B, C, and D marked in the energy carbon sensitive map. The temperature and humidity offset of the region is extracted, for example, the average temperature of area A is 25℃, the humidity is 60%RH, the average temperature of area B is 26℃, the humidity is 55%RH, the average temperature of area C is 23℃, the humidity is 70%RH, the average temperature of area D is 22℃, the humidity is 65%RH, and the carbon emission gradient, for example, the carbon emission gradient of area A is 0.05kg / m³ / s, area B is 0.06kg / m³ / s, area C is 0.02kg / m³ / s, and area D is 0.03kg / m³ / s. The local high energy consumption areas A and B are morphologically aggregated. If A and B are adjacent in space and have similar energy consumption characteristics, they will be aggregated into a larger optimization area block AB. The low efficiency areas C and D are morphologically aggregated to obtain the optimization area block CD. According to the building HVAC system diagram, the air conditioning units, fans, pipes and other equipment operation structures in the building are divided, for example, the air conditioning units serving area AB are divided into a device operation structure unit 1, and the air conditioning units serving area CD are divided into a device operation structure unit 2. The optimization detail block partition data containing optimization detail block partition (such as AB, CD) and device operation structure division (such as unit 1, unit 2) is generated.

[0061] The energy consumption recognition sub-module calls the optimization detail block partition, extracts the partition energy consumption frequency distribution and carbon emission boundary data, recognizes the temperature and humidity change rate and boundary displacement rate, and filters according to the energy consumption difference threshold and carbon emission boundary change judgment standard to obtain the energy consumption mapping region set.

[0062] The optimization detail block partition data is received, such as including optimization area blocks AB and CD, and device operation structure units 1 and 2, the energy consumption frequency distribution of the partition AB and CD in the past period of time is extracted, such as by analyzing historical energy consumption data, it is obtained that the energy consumption of the area AB is mainly concentrated in the morning 9 o'clock to the afternoon 5 o'clock, and the energy consumption frequency distribution of the area CD is relatively gentle, the carbon emission boundary data of the partition AB and CD is extracted, such as by carbon emission sensor monitoring, the carbon emission concentration difference of the area AB and adjacent area is formed, the temperature and humidity change rate in each partition is identified, such as the temperature change range of the area AB in a day is 24 DEG C to 26 DEG C, the humidity change range is 55% RH to 60% RH, the temperature change rate is 2 DEG C / day, and the humidity change rate is 5% RH / day, the displacement rate of the carbon emission boundary is identified, such as by continuously monitoring the carbon emission concentration distribution, the carbon emission boundary of the area AB moves 0.5 m / h to the adjacent area in a period, the energy consumption difference threshold is set to 20% (for example, if the average energy consumption of a region is significantly higher than that of the region 20%), the carbon emission boundary change criterion is 0.3 m / h (for example, if the carbon emission boundary moving rate exceeds 0.3 m / h, it is considered that the boundary changes significantly), each partition is screened according to the threshold and the criterion, such as if the average energy consumption of the area AB is 25% higher than that of the region, and the carbon emission boundary displacement rate reaches 0.4 m / h, the area AB is determined as an energy consumption mapping region, and finally an energy consumption mapping region set including one or more energy consumption mapping regions is obtained, such as {AB}.

[0063] The mapping generation submodule extracts building environment features and device operation features according to the energy consumption mapping region set, compares the temperature and humidity distribution vector in the region with the carbon emission response tensor, and uses the formula:

[0064] ;

[0065] The optimization intensity value between regions is calculated, the optimization intensity is taken as the basis to execute feature mapping index combination, and the optimization mapping association group is generated;

[0066] representing the optimization intensity value between regions, representing the temperature of the i-th region, representing the temperature average value of the region, representing the humidity of the i-th region, representing the humidity average value of the region, representing the coefficient of the carbon emission response tensor of the i-th region, representing the number of regions;

[0067] The inter-regional optimization intensity value represents the degree of deviation of the temperature and humidity distribution in the region from its average value, and the degree of quantitative index calculated after considering the sensitivity of the carbon emission response of the region, the higher the value, the greater the fluctuation of the current temperature and humidity environment state of the region relative to its average level, and the more sensitive the impact on carbon emissions, so it needs to be prioritized for energy optimization intervention. By comparing the optimization intensity values of each region, the key areas with low energy utilization efficiency or poor environmental comfort in the building can be identified, providing important quantitative basis for subsequent development of precise energy regulation strategies.

[0068] The mapping energy consumption mapping region set {AB} is extracted, and the building environment characteristics, such as the region AB being mainly an office with high personnel density and the window facing south, and the equipment operation characteristics, such as the air conditioning unit serving the region AB being of type XXX with a set temperature distribution vector of , where represents the temperature value of the i-th position in the region, such as (25℃, 25.5℃, 24.8℃), the humidity distribution vector is , where represents the humidity value of the i-th position in the region, such as (60%RH, 58%RH, 62%RH), and the coefficient of the carbon emission response tensor reflects the sensitivity of the carbon emission of the region to the change of temperature and humidity, for example, according to historical data analysis, the carbon emission response tensor coefficient of region AB is (0.8, 0.9, 0.7), and the number of regions n=3.

[0069] The temperature average value of the region is calculated as .

[0070] The humidity average value is .

[0071] Substitute the above values into the formula:

[0072]

[0073]

[0074] The optimization intensity value of region AB is calculated as 3.85. Based on this optimization intensity value, perform feature mapping index combination, such as associating the optimization intensity value with the region ID, environmental characteristics, equipment operation characteristics, etc., to generate an optimization mapping association group, such as {(region ID: AB, optimization intensity: 3.85, environmental characteristics: {personnel density: high, orientation: south}, equipment characteristics: {air conditioner type: XXX}).

[0075] Please refer to Figure 4The structure energy efficiency mapping module comprises:

[0076] The structure layer extraction submodule extracts the arrangement matrix of the space region and the energy flow direction diagram in the building according to the optimization mapping correlation group, identifies the carbon flow direction offset vector in the equipment operation, compares the distribution change amount of the two at the same space position, arranges the building region according to the gradient difference, generates an optimization guide space hierarchy diagram, and the like.

[0077] The optimization mapping correlation group is received, for example, {(region ID: AB, optimization intensity: 3.85, environmental characteristics: {personnel density: high, orientation: south}, equipment characteristics: {air conditioner model: XXX})}, the spatial region arrangement matrix of region AB is extracted from the BIM model of the building, for example, the AB region is composed of a 3x2 grid, represented as [[1, 1, 1], [1, 1, 1]]. The energy flow direction diagram is extracted, for example, by analyzing the air supply and exhaust mode of the ventilation system, the equipment operation state and the personnel activity distribution, it is obtained that the energy flow of the AB region mainly transmits from north to south, the energy flow is converted by combining the emission factor to form the carbon flow intensity and direction diagram. Identify the energy flow direction offset vector existing in the air conditioning equipment operation serving the AB region, for example, due to unstable operation of the fan or changes in indoor layout, the energy flow direction of the local region deviates from the overall transmission direction, which is quantified as an offset vector (-0.1, 0.2) (indicating the offset ratio in the x and y directions), compare the distribution change amount of the spatial region arrangement matrix and the energy flow direction diagram at the same space position, for example, compare whether the energy flow direction in each grid unit is consistent with the overall transmission direction, and count the number of inconsistent grids. Arranging the building region according to the gradient difference, for example, according to the optimization intensity value and the size of the energy flow (and converted carbon flow) offset, the building region is divided into high optimization demand area, medium optimization demand area and low optimization demand area, an optimization guide space hierarchy diagram is generated, and the optimization demand degree of each region is displayed in different colors or levels, for example, the AB region is marked as a high optimization demand area.

[0078] The active region identification submodule extracts the carbon flow density diagram and the carbon flow direction offset diagram according to the optimization guide space hierarchy diagram, judges the local density gradient section, and selects the high fluctuation segment region according to the offset amplitude difference value, using the formula: ;

[0079] The high fluctuation value of the region is calculated, and the corresponding position is marked as a high energy consumption structure area or an inefficient structure area, and a building structure energy efficiency layering table is obtained.

[0080] Among them, represents the high fluctuation value of the region, represents the carbon flow density gradient of the i-th section, represents the carbon flow direction offset of the i-th section, represents the number of regions;

[0081] The high fluctuation value of the region is a quantitative index for measuring the instability of the energy consumption state of a specific region in the building space and the potential optimization space, which is obtained by calculating the dot product of the carbon flow density gradient vector and the carbon flow direction deviation vector of the region and normalizing the dot product. The absolute value of the dot product reflects the correlation between the degree of change in carbon flow density and the degree of deviation from the flow direction. The larger the absolute value, the more unstable the carbon flow characteristics of the region. Normalization allows the fluctuation values of different regions to be compared on the same scale. Therefore, a higher value indicates that the energy consumption behavior of the region has greater fluctuation, indicating energy waste or inefficient operation, which needs to be identified as a high-energy consumption or inefficient structure region and prioritized for optimization measures to improve energy efficiency.

[0082] According to the optimization guide space hierarchy diagram (for example, region AB is marked as a high optimization demand area), the carbon flow density map of region AB is extracted, for example, by obtaining the carbon flow density distribution of each location through a carbon emission sensor network, and the density size is represented by different color depths. The carbon flow direction deviation map is extracted, which shows the deviation of the carbon flow direction at each location from the main direction. The section with a large local carbon flow density gradient is determined, for example, the carbon flow density is high near the air supply outlet, forming a high-density gradient section. According to the carbon flow direction deviation map, the area with a large deviation amplitude difference is selected, for example, due to poor air distribution in some corners, the carbon flow direction is chaotic, and the deviation amplitude is large. The carbon flow density gradient is set to , the carbon flow direction deviation is , and the number of regions n=5 (assuming that region AB is divided into 5 small sections for analysis). The carbon flow density gradient vector and direction deviation vector of each section are shown in Table 1:

[0083] Table 1: Carbon flow density gradient and direction deviation vector of each section of region AB

[0084]

[0085] The high fluctuation value of each region is calculated according to the formula : ;

[0086] For section 1:

[0087] ;

[0088] For section 2:

[0089] ;

[0090] For section 3:

[0091] ;

[0092] For section 4:

[0093] ;

[0094] For section 5:

[0095] ;

[0096] The sum term is:

[0097] ;

[0098] The ΔP value of each section is:

[0099] ;

[0100] ;

[0101] ;

[0102] ;

[0103] ;

[0104] Set the high volatility threshold to 0.5, then and Exceed the threshold, mark sections 3 and 5 as high energy consumption structure area or low efficiency structure area, and finally get the building structure energy efficiency stratification table, which lists the high volatility value of each area and the corresponding energy efficiency rating, as shown in Table 2:

[0105] Table 2: Building structure energy efficiency stratification table

[0106]

[0107] The results show that the correlation between the carbon flow density gradient and the direction offset of section 3 in area AB is relatively high, and the volatility is large, which is identified as a high energy consumption structure area, and the volatility of section 5 is also relatively high, which is identified as a low efficiency structure area. The area needs to be paid attention to and take corresponding optimization measures, the calculation of high volatility value is measured by the absolute value of the dot product of carbon flow density gradient and direction offset, and normalized processing is carried out, which is used to evaluate the energy consumption instability and potential optimization space of local area. The higher the high volatility value, the more unstable the energy consumption characteristics of the area, and there is a high energy waste or low efficiency operation.

[0108] Please refer to Figure 5 , the space-time matching screening module includes:

[0109] The structure scale calibration sub-module calls the building structure energy efficiency hierarchical table, extracts the hierarchical distribution of high-frequency carbon flow areas and low-frequency stationary areas in the building, divides the structure unit boundary according to the temperature and humidity response intensity gradient value, and generates the structure unit scale interval;

[0110] The building structure energy efficiency hierarchical table is called, which lists the energy efficiency ratings of each area, such as high-energy consumption structure area (section 3), low-frequency stationary area (for example, section 1 and 2 with normal energy efficiency rating), the hierarchical distribution of the marked high-frequency carbon flow area (corresponding to the high-energy consumption structure area) and the low-frequency stationary area in the building is extracted, for example, the high-frequency carbon flow area is mainly concentrated on the south side of the building, and the low-frequency stationary area is distributed on the north side, the structure unit boundary is divided according to the temperature and humidity response intensity gradient value, for example, between adjacent areas, if the temperature or humidity response intensity gradient exceeds the set threshold (for example, 5℃ / m or 10%RH / m), the place is divided into a structure unit boundary, the structure unit scale interval is generated, for example, the south high-frequency carbon flow area is divided into several smaller structure units, and the scale of each unit is between 2 meters and 5 meters, while the north low-frequency stationary area can be divided into larger structure units, and the scale is between 5 meters and 10 meters.

[0111] The style domain analysis sub-module extracts the temperature and humidity histogram amplitude under the differential period based on the structure unit scale interval, detects the carbon flow symbiotic matrix change rate between adjacent periods, and establishes a multi-period style domain set;

[0112] Based on the structure unit scale interval (for example, south unit scale 2-5 meters, north unit scale 5-10 meters), the temperature and humidity histogram amplitude under the differential period is extracted, for example, the temperature and humidity data of each structure unit in different periods such as summer noon and winter morning are extracted respectively, the histogram is drawn, and the amplitude distribution characteristics are obtained. The energy flow transfer matrix change rate between adjacent periods is detected, and the energy flow is converted into carbon emission based on the emission factor to form a carbon flow symbiotic matrix, for example, the change rate of energy flow transfer amount and corresponding carbon emission amount between adjacent two hours is calculated, and a multi-period style domain set is established, which contains the temperature and humidity histogram amplitude of each structure unit in different periods and the carbon flow symbiotic matrix change rate formed based on the energy flow transfer matrix conversion. Information such as.

[0113] The style matching degree calculation sub-module calls the multi-period style domain set, and uses the formula:

[0114] ;

[0115] The spatiotemporal correspondence relationship matching degree value is calculated, the coincidence proportion threshold of each style domain is compared, and the spatiotemporal correspondence relationship list is generated;

[0116] wherein, represents the spatiotemporal correspondence relationship matching degree value, the overlapping area of the Kth pattern field, the temperature data of the Kth pattern field, the humidity data of the Kth pattern field, the reference overlapping proportion threshold of the Kth pattern field, the maximum area value of the pattern field, and N represents the total number of pattern fields;

[0117] The spatiotemporal correspondence matching degree value is an index for measuring the correlation degree between the energy use mode of different areas inside the building and external environmental factors (such as climate, temperature change, etc.) in a specific period. The value is calculated by comparing the energy consumption data in the region and the change trend of external environmental variables in space and time, and the matching degree is evaluated. The higher the matching degree value, the stronger the synchronization between the energy use of the region and the external environmental change, which means that the region can effectively respond to the change of the external environment, and the energy consumption adjustment is reasonable. A lower matching degree value indicates that the energy consumption change in the region deviates from the spatiotemporal characteristics of the external environment, resulting in low energy utilization efficiency or unreasonable energy consumption fluctuations. Through the analysis of the value, the energy use mode inside the building can be more accurately adjusted and optimized, and the overall energy efficiency can be improved. A multi-period pattern field set is called, which contains the temperature and humidity histogram amplitude information of each structural unit in different time periods. The overlapping area of the Kth pattern field is set to 5 m2. The overlapping area is the area with similar temperature and humidity distribution in different periods. The temperature data of the Kth pattern field is 25℃, the humidity data is 60% RH, the reference overlapping proportion threshold of the Kth pattern field is 0.8, the maximum area value of the pattern field is 10 m2, and it is assumed that there are N=3 pattern fields.

[0118] Substitute the numerical values into the formula to calculate the spatiotemporal correspondence matching degree value M:

[0119] ;

[0120] ​​​​​If the calculated overlap ratio is less than the threshold value, it is considered that the spatio-temporal correspondence is poor, and a spatio-temporal correspondence list is generated, which lists the spatio-temporal correspondence matching degree values of each structural unit in different time periods. By comprehensively considering the overlap area, temperature and humidity data, and reference overlap ratio threshold value, and introducing the ratio to the maximum area as a penalty term, the matching degree of the space region in different time periods can be more accurately evaluated, so as to identify the region with unstable spatio-temporal characteristics. The results show that the calculated spatio-temporal correspondence matching degree value is 34.247, which reflects the overall matching degree of the building space style domain in different time periods. A higher matching degree value may mean that the spatio-temporal characteristics are more stable, and vice versa. This value will be used as the basis for subsequent input to guide the development of energy regulation strategies.

[0121] Please refer to Figure 6 , the regulation fusion module comprises:

[0122] The temperature and humidity balancing submodule extracts the temperature and humidity channel values of the building block, calls the spatio-temporal correspondence list to determine the region scale level, compares the temperature and humidity distribution of the building block according to the level temperature and humidity reference value, adjusts the channel value deviating from the reference, and obtains the temperature and humidity distribution weight;

[0123] By collecting real-time temperature and humidity data of each region in the building block, the temperature and humidity channel value of each region is obtained, which represents the temperature and humidity data in a specific region, and there is fluctuation and deviation from the existing reference value. By calling the spatio-temporal correspondence list, the data is classified according to the distribution characteristics of time and space, the corresponding region scale level (such as the interior of a building, a floor or a specific room, etc.) is determined, and the channel value is compared with the preset temperature and humidity reference value. For example, assuming that the reference temperature of a certain region is 22℃ and the humidity is 50%, while the actual measured temperature is 23℃ and the humidity is 55%. By comparing, it is found that the temperature is 1℃ higher and the humidity is 5% higher, so adjustment is needed. The adjustment process is completed by weighted average method or proportional adjustment method, so as to correct the temperature and humidity data of the region, ensure that it is closer to the ideal reference value, and generate the temperature and humidity distribution weight according to the adjustment value of each region, reflect the temperature and humidity distribution of each region, and provide data support for subsequent carbon emission identification and energy consumption regulation.

[0124] The carbon emission identification submodule extracts the carbon emission gradient value and the temperature and humidity difference value of the building block based on the temperature and humidity distribution weight, screens the key carbon emission region, compares and identifies the response intensity and the gradient difference ratio of the adjacent region, and obtains the carbon emission continuity measurement map;

[0125] The carbon emission continuity measurement map is called, and the energy consumption intensity value and the environmental priority value of each building block are combined to allocate different control strategies to different regions. For example, the energy consumption intensity of a certain region is high, and its environmental priority value is large, indicating that the energy consumption of this region has a significant impact on the environment, so this region is given priority for control. According to the preset energy consumption retention threshold, it is judged whether the energy consumption of each region meets the optimization standard. The energy consumption retention threshold is set to 30%, that is, if the energy consumption of a certain region is higher than the threshold, the carbon emission activation factor is activated to intensively control the region. The role of the carbon emission activation factor is to optimize the energy use structure of the region by adjusting the energy allocation in the region to reduce carbon emissions. For example, if the energy consumption intensity value of a certain region is 120 kWh / m²·year, the environmental priority value is 8, and the energy consumption exceeds the retention threshold, the system will start the activation factor, and through optimization and control, the energy consumption of the region will be reduced to 100 kWh / m²·year, thereby reducing the carbon emissions of the region. According to the control requirements of each region, an energy and carbon emission control framework for the building is generated, which serves as the basis for energy efficiency improvement and carbon emission optimization.

[0126] The carbon emission continuity measurement map is called, and the energy consumption intensity value and the environmental priority value of each building block are combined to allocate different control strategies to different regions. For example, the energy consumption intensity of a certain region is high, and its environmental priority value is large, indicating that the energy consumption of this region has a significant impact on the environment, so this region is given priority for control. According to the preset energy consumption retention threshold, it is judged whether the energy consumption of each region meets the optimization standard. The energy consumption retention threshold is set to 30%, that is, if the energy consumption of a certain region is higher than the threshold, the carbon emission activation factor is activated to intensively control the region. The role of the carbon emission activation factor is to optimize the energy use structure of the region by adjusting the energy allocation in the region to reduce carbon emissions. For example, if the energy consumption intensity value of a certain region is 120 kWh / m²·year, the environmental priority value is 8, and the energy consumption exceeds the retention threshold, the system will start the activation factor, and through optimization and control, the energy consumption of the region will be reduced to 100 kWh / m²·year, thereby reducing the carbon emissions of the region. According to the control requirements of each region, an energy and carbon emission control framework for the building is generated, which serves as the basis for energy efficiency improvement and carbon emission optimization.

[0127] The carbon emission continuity measurement map is called, and the energy consumption intensity value and the environmental priority value of each building block are combined to allocate different control strategies to different regions. For example, the energy consumption intensity of a certain region is high, and its environmental priority value is large, indicating that the energy consumption of this region has a significant impact on the environment, so this region is given priority for control. According to the preset energy consumption retention threshold, it is judged whether the energy consumption of each region meets the optimization standard. The energy consumption retention threshold is set to 30%, that is, if the energy consumption of a certain region is higher than the threshold, the carbon emission activation factor is activated to intensively control the region. The role of the carbon emission activation factor is to optimize the energy use structure of the region by adjusting the energy allocation in the region to reduce carbon emissions. For example, if the energy consumption intensity value of a certain region is 120 kWh / m²·year, the environmental priority value is 8, and the energy consumption exceeds the retention threshold, the system will start the activation factor, and through optimization and control, the energy consumption of the region will be reduced to 100 kWh / m²·year, thereby reducing the carbon emissions of the region. According to the control requirements of each region, an energy and carbon emission control framework for the building is generated, which serves as the basis for energy efficiency improvement and carbon emission optimization.

[0128] The above merely describes the preferred embodiments of the present application, and is not intended to limit the present application in other forms. Any skilled person in the art can modify or change the disclosed technical content into equivalent embodiments with equivalent changes, and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application, without departing from the technical solution content of the present application, still falls within the protection scope of the present application.

Claims

1. A building carbon hub adaptive AI control system, characterized in that, The system comprises: The carbon-sensitive analysis module obtains building environment and equipment operation state information, receives temperature and humidity data of rooms and public areas in the building in real time, calculates temperature and humidity gradient and its change rate, energy flow path and structure compatibility distribution coefficient, combines carbon flow overflow rate and direction consistency, identifies high energy consumption and low efficiency areas through clustering, extracts energy consumption and carbon flow distribution density and dynamic migration path in space, labels high energy consumption and low efficiency areas in the building by comparing energy flow direction and carbon flow continuity in the area, and generates carbon-sensitive atlas; The optimization strategy calculation module calls the carbon-sensitive atlas, divides equipment operation detail blocks, identifies energy consumption difference rate and carbon emission boundary offset, selects areas meeting threshold value as optimization coverage unit, performs energy and carbon bidirectional mapping comparison, calculates optimization intensity value between areas, and generates optimization mapping correlation group; The structure energy efficiency mapping module extracts building space structure hierarchy corresponding to equipment operation carbon flow direction offset according to the optimization mapping correlation group, judges energy efficiency change section, demarcates activity area and reference area, calculates area high volatility value, and obtains building structure energy efficiency hierarchical table; The space-time matching screening module calls the building structure energy efficiency hierarchical table, selects building operation unit scale range, identifies multi-period carbon emission style area, compares coincidence proportion of temperature and humidity consistency and energy consumption frequency difference, screens optimal matching style area, calculates space-time corresponding relationship matching degree value, and generates space-time corresponding relationship list; The regulation fusion module calls the space-time corresponding relationship list, and in the regulation process, calculates temperature and humidity balance, carbon emission response and energy consumption intensity of each unit building block, combines environment and equipment weight cross analysis, sets energy consumption retention threshold and carbon emission activation factor, and generates building energy and carbon emission regulation framework; The building energy and carbon emission regulation framework comprises a temperature and humidity balance layer, a carbon emission response distribution graph, an energy consumption intensity adjustment factor, and an energy consumption retention weight setting table.

2. The architectural carbon hub adaptive Al control system of claim 1, wherein, The carbon-sensitive atlas comprises energy flow main direction distribution density, carbon flow continuity grade identification, area efficiency label, and energy consumption response feature map. The optimization mapping correlation group comprises optimization coverage area number, energy consumption difference comparison item, carbon emission boundary offset record, and mapping corresponding index table. The building structure energy efficiency hierarchical table comprises structure level number, carbon flow direction mapping relationship, energy efficiency change section label, structure stability parameter, and active area positioning marker. The space-time corresponding relationship list comprises scale matching range set, style domain selection list, energy consumption frequency coincidence coefficient, and temperature and humidity feature overlap rate index.

3. The architectural carbon hub adaptive Al control system of claim 1, wherein, The energy consumption mapping extraction submodule obtains building environment and equipment operation state information, extracts temperature gradient value and humidity channel offset value in the corresponding area, compares average amplitude of temperature gradient value and standard deviation of humidity channel offset value in the area, and generates energy consumption migration tendency value. The structure continuity evaluation submodule identifies temperature and humidity gradient change rate and carbon flow communication section length in the building area based on the energy consumption migration tendency value, compares density distribution of temperature and humidity gradient change rate and variation interval of communication section length, and obtains structure compatibility distribution coefficient. ​ The sensitive area calibration sub-module extracts carbon flow overflow rate and direction consistency value in the building according to the structure compatible distribution coefficient, filters the area aggregation distribution of the carbon flow overflow rate and direction consistency value, calibrates high energy consumption areas and low efficiency areas, and generates an energy carbon sensitive map.

4. The architectural carbon hub adaptive Al control system of claim 3, wherein, The optimization strategy calculation module comprises: The map division sub-module calls the energy carbon sensitive map, extracts building structure blocks and energy carbon clustering areas, extracts temperature and humidity offset degree and carbon emission gradient, performs local area shape aggregation and block division, and performs equipment operation structure division to generate an optimization detail block partition; The energy consumption identification sub-module calls the optimization detail block partition, extracts partition energy consumption frequency distribution and carbon emission boundary data, identifies temperature and humidity change rate and boundary displacement rate, filters according to energy consumption difference threshold and carbon emission boundary change judgment standard, and obtains an energy consumption mapping area set; The mapping generation sub-module extracts building environment features and equipment operation features according to the energy consumption mapping area set, compares temperature and humidity distribution vectors and carbon emission response tensors in the area, and uses the formula: ; Calculate the optimization intensity value between areas, use the optimization intensity as the basis to perform feature mapping index combination, and generate an optimization mapping correlation group; representing an optimization strength value between regions, representing a temperature of the i-th region, representing a temperature average value of the region, representing a humidity of the i-th region, representing a humidity average value of the region, representing a coefficient of a carbon emission response tensor of the i-th region, representing a number of regions.

5. The architectural carbon hub adaptive Al control system of claim 4, wherein, The structure energy efficiency mapping module comprises: The structure layer extraction sub-module extracts the arrangement matrix of the space area in the building and the energy flow direction graph according to the optimization mapping correlation group, identifies the carbon flow direction offset vector in the equipment operation, compares the distribution change amount of both at the same space position, arranges the building area according to the gradient level difference, and generates an optimization guide space hierarchy graph; The active area identification sub-module extracts the area carbon flow density graph and the carbon flow direction offset graph according to the optimization guide space hierarchy graph, judges the local density gradient section, and screens the high fluctuation segment area according to the offset amplitude difference value, and uses the formula: ; Calculate the area high fluctuation value, mark the corresponding position as a high energy consumption structure area or a low efficiency structure area, and obtain a building structure energy efficiency layering table; wherein, a high volatility value representative of a region, a carbon flow density gradient representative of the i-th section, a carbon flow direction offset representative of the i-th section, a number of regions.

6. The architectural carbon hub adaptive Al control system of claim 5, wherein, The space-time matching filtering module comprises: The structure scale calibration sub-module calls the building structure energy efficiency layering table, extracts the hierarchical distribution of high-frequency carbon flow areas and low-frequency stable areas in the building, divides the structure unit boundary according to the temperature and humidity response intensity gradient value, and generates a structure unit scale interval; The style domain analysis sub-module extracts the temperature and humidity histogram amplitude in the differential period based on the structure unit scale interval, detects the carbon flow symbiotic matrix change rate between adjacent periods, and establishes a multi-period style domain set; The style matching degree calculation sub-module calls the multi-period style domain set, uses the formula: ; Calculate the space-time corresponding relationship matching degree value, compare the coincidence proportion threshold of each style domain, and generate a space-time corresponding relationship list; M represents a spatio-temporal correspondence matching degree value, represents the area of the overlapping region of the Kth style domain, represents the temperature data of the Kth style domain, represents the humidity data of the Kth style domain, represents the reference overlapping proportion threshold value of the Kth style domain, represents the maximum area value of the style domain, and N represents the total number of style domains.

7. The architectural carbon hub adaptive Al control system of claim 1, wherein, The regulation and control fusion module comprises: The temperature and humidity balancing sub-module extracts the temperature and humidity channel value of the building block, calls the space-time corresponding relationship list to determine the area scale level, compares the temperature and humidity distribution of the building block according to the level temperature and humidity reference value, adjusts the channel value deviating from the reference, and obtains the temperature and humidity distribution weight; The carbon emission identification submodule extracts the carbon emission gradient value and the temperature and humidity difference value based on the temperature and humidity distribution weight, screens the key carbon emission area, compares and identifies through the response intensity and the adjacent area gradient difference ratio, and obtains a carbon emission continuity measurement map; The carbon emission continuity measurement map, the energy consumption intensity value of each building block, and the environmental priority value are called by the energy-carbon fusion submodule, the energy consumption reservation threshold and the carbon emission activation factor are combined, the building blocks are regulated and distributed according to the regional scale, and a building energy and carbon emission regulation framework is generated.

Images