Low-carbon building monitoring system and method based on digital twinning

Abstract

The invention discloses a low-carbon building monitoring system and method based on digital twinning, and relates to the technical field of digital twinning, the system comprises a data acquisition unit, a computing power cooperation unit, a regulation and control execution unit and a user interaction unit, the data acquisition unit carries out regional targeted timing monitoring, builds a unified semantic standard and a dynamic knowledge graph, and sends the unified semantic standard and dynamic knowledge graph to the user interaction unit; the comprehensiveness and efficiency of data association analysis are improved; a three-level computing power collaboration system is constructed through the computing power collaboration unit, building monitoring information is integrated, complex simulation of a digital twin module is carried out, an energy transmission path and equipment fault risks are accurately tracked, prediction optimization and long-term regulation and control management are carried out, and the construction efficiency is improved. Therefore, a full-life-cycle integrated management framework in a macroscopic geographical environment, a mesoscopic energy link and microscopic equipment of a building cluster is built, cross-domain collaborative analysis is realized, the real-time requirement is met, multi-target optimization design for balancing energy cost, energy efficiency and comfort is realized, and carbon neutralization targets in the building industry are assisted to fall into the ground.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a low-carbon building monitoring system and method based on digital twin. Background Art

[0002] Digital twin is an innovative concept and method that integrates multiple cutting-edge technologies. It creates a virtual mapping body for physical entities, processes or systems in a digital way. This virtual body can synchronize the status, operating data, environmental parameters and other information of the physical object in real time, and predict and simulate the future development trend of the physical object through algorithmic models. Low-carbon building monitoring systems and methods based on digital twins have shown significant potential in promoting building energy efficiency and carbon emission reduction, but their actual application still faces multi-dimensional technical bottlenecks and systemic challenges.

[0003] In traditional systems, multi-source data such as building structures, energy pipelines, and environmental monitoring have data silos due to inconsistent semantic standards. There is a lack of an integrated management framework for the entire life cycle of building clusters, including the macro-geographical environment, the meso-level energy links, and the micro-level internal equipment. It is impossible to accurately track energy transmission paths and equipment failure risks, making it difficult to achieve cross-domain collaborative analysis and meet real-time requirements. In addition, building energy consumption is affected by dynamic factors such as weather, user behavior, and equipment aging, which will lead to a delayed response to dynamic changes in the environment and behavior.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem of "data islands" existing in the prior art due to the lack of unified semantic standards for multi-source data, the lack of an integrated management framework for the entire life cycle of the building cluster's macro-geographical environment, meso-energy links, and micro-equipment internals, the inability to accurately track energy transmission paths and equipment failure risks, the difficulty in achieving cross-domain collaborative analysis and meeting real-time requirements, and the fact that building energy consumption is affected by dynamic factors such as weather, user behavior, and equipment aging, which will lead to a delayed response to dynamic changes in the environment and behavior.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A low-carbon building monitoring method based on digital twins includes the following steps: Step 1: Collect building monitoring information: By setting the information collection cycle and marking the key nodes of the building, the building monitoring information can be monitored regularly in a targeted manner. The building monitoring information includes building accessory monitoring parameters and environmental behavior monitoring parameters. Step 2: Integrate building monitoring information: Build a multi-source unified data model through semantic mapping and knowledge graph, obtain multi-source fusion standardized data, and transmit and share data; Step 3: Build a digital twin model: Build a three-dimensional dynamic digital twin model through building accessory monitoring parameters, and update the data in real time; Step 4: Establish a hybrid prediction model: Dynamically predict building energy consumption and equipment operating status by integrating standardized data from multiple sources, and conduct coordinated control and optimization of the building energy system to obtain low-carbon building regulation optimization solutions and corresponding optimization control instructions; Step 5: Receive optimization control instructions: Use optimization control instructions to control the building's energy equipment and environmental conditioning equipment in real time, thereby accurately adjusting the building's operating status in different regions; Step 6: Visual query and behavioral interaction: Users use the visual interface to query building monitoring information and low-carbon building control optimization plans in real time, and input personalized behavioral preferences to dynamically adjust user behavior data.

[0007] Furthermore, the specific process of collecting building monitoring information is as follows: Building accessory monitoring parameters include building structure data, energy network data, and equipment operation data; Environmental behavior monitoring parameters include environmental weather data and user behavior data; Collect building monitoring information through multi-source sensor monitoring; Building structure data includes basic geometric indicators, spatial relationship indicators, and complex shape indicators; energy network data includes network indicators and energy consumption indicators; equipment operation data includes operation indicators and performance indicators; Environmental weather data includes environmental indicators and meteorological indicators; user behavior data includes personnel activity indicators and energy preference indicators.

[0008] Furthermore, the specific process of integrating building monitoring information is as follows: S2-1, the specific process of pre-processing building monitoring information is as follows: Preprocessing of building structure data and equipment operation data: missing values ​​are processed by linear interpolation of adjacent data points, and outlier determination is performed using the 3σ principle; Preprocessing energy network data and environmental weather data: Build an LSTM neural network using historical data and time series to obtain predicted values. This is combined with the collected data to assess data deviations. Data deviation thresholds are then set and compared to identify outliers. Preprocessing user behavior data: Build an LSTM neural network based on historical data and time series data to obtain and mark the reasonable interval of user behavior data. When the detection value of the collected user behavior data exceeds the reasonable interval, it is determined to be an outlier. For data outliers identified in pre-processing, manual verification is performed to retest the data to correct the outliers and normalize the data to remove the dimension of the parameter indicators. S2-2, develop unified semantic standards by analyzing building monitoring information: Integrate building monitoring information with construction industry standards and international common data standards to develop a unified semantic vocabulary covering building accessory monitoring parameters and environmental behavior monitoring parameters; S2-3, establish semantic mapping rules by analyzing the semantic differences of multi-source sensors: Establish mapping rules from the semantics of sensor raw data to a unified semantic standard, thereby converting data into standard units; S2-4, set and mark the knowledge graph entities and the relationships between them, build the knowledge graph and update it dynamically: Knowledge graph entities include building structures, energy networks, equipment, environment, and users; relationships between entities include connection relationships, usage relationships, and impact relationships; Through natural language processing (NLP) technology and machine learning algorithms, entities and relationships are extracted from the collected building monitoring information to build a knowledge graph; Establish a dynamic update mechanism for the knowledge graph and regularly check and optimize the knowledge graph for consistency; S2-5, then perform spatiotemporal alignment by aligning timestamps with unified geographic coordinates to obtain multi-source fused standardized data.

[0009] Furthermore, the specific process of building a digital twin model is as follows: Establish a multi-scale, full-life cycle management mechanism for building clusters, including macro-scale, meso-scale and micro-scale; The macro-scale is constructed by integrating the 3D geographic information system and the building information model. Environmental weather data is input through 3D-GIS to build a macro spatial framework of the building's geographical location and surrounding environment. The building structure data is input through BIM to mark the building structure zoning. At the mesoscale, energy network data is used to build digital links between equipment, networks, and energy consumption. This connects building floor equipment with the energy network and labels all equipment and networks, allowing for real-time tracking of energy transmission paths and calculation of losses. At the micro scale, the internal structure of the equipment is modeled and the equipment operation data is input to predict the probability of equipment failure, and then the risk level of the equipment is determined and a corresponding risk warning signal is generated.

[0010] Furthermore, the specific process of establishing a hybrid prediction model is as follows: Dynamically predict building energy consumption and equipment operating status through multi-source fusion of standardized data; Analyze and obtain dynamic space-energy coupling feature vectors through building structure data, energy network data and equipment operation data ; Analyze and obtain multi-scale time series-behavior feature fusion vectors through environmental weather data and user behavior data ; The dynamic space-energy coupling eigenvector and multi-scale temporal-behavioral feature fusion vector Perform splicing and obtain splicing feature vector , and perform time series prediction through the LSTM deep learning model to obtain the prediction output vector .

[0011] Furthermore, the dynamic space-energy coupling eigenvector is obtained The specific process is: Dynamically predict building energy consumption and equipment operating status through multi-source fusion of standardized data; Extract building geometric features G through building structure data, and extract dynamic topological features T(t) through energy network data and equipment operation data; Through the historical data analysis and linear regression fitting, the weight factors of dynamic topological features T(t) and building geometric features G are obtained and marked as 、 ; Then, the dynamic space-energy coupling feature vector is obtained by weighted synthesis of the dynamic topological feature T(t) and the building geometric feature G and its corresponding weight factors. .

[0012] Furthermore, we obtain the multi-scale temporal-behavior feature fusion vector The specific process is: Extract environmental time series features E(t) through environmental weather data, and extract user behavior features B(t) through user behavior data; Construct the behavior cluster center Ck through semantic mapping, mark the number of behavior patterns as K, mark any behavior pattern as k, obtain the behavior alignment function through the knowledge graph and mark it as Align; By calculating the energy consumption fluctuation variance of the building under different behavior modes, the behavior mode weight is set ; The wavelet transform function WT is used to decompose the environmental time series features E(t) into multi-scale time series, and combined with the user behavior features B(t), behavior cluster center Ck, behavior alignment function Align, behavior pattern weight , thereby obtaining the multi-scale time series-behavior feature fusion vector .

[0013] Furthermore, the specific process of obtaining the low-carbon building regulation optimization plan and the corresponding optimization control instructions is as follows: Set the equipment control instruction U as the action space to regulate the equipment of the building; The energy cost coefficient C(U) is obtained by combining the energy consumption of the equipment with the unit price of electricity, and the network flow rate with the unit price of energy. The energy efficiency index coefficient E(U) is obtained by the user comfort contribution per unit energy consumption. The comfort deviation coefficient D(U) is obtained by the deviation between the actual comfort data value and the comfort range. Then, the weight coefficients of the energy cost coefficient C(U), the energy efficiency index coefficient E(U) and the comfort deviation coefficient D(U) are set to output the multi-objective optimization function; By taking the minimum value of the multi-objective optimization function, the corresponding equipment control instruction U is the optimization control instruction of the low-carbon building regulation optimization solution.

[0014] A low-carbon building monitoring system based on digital twins, comprising a data acquisition unit, a computing power coordination unit, a control execution unit, and a user interaction unit, wherein the data acquisition unit, the computing power coordination unit, the control execution unit, and the user interaction unit are communicatively connected to each other, and the system executes the above-mentioned low-carbon building monitoring method based on digital twins; The data acquisition unit is used to collect building monitoring information: by setting the information collection cycle and marking the key nodes of the building, the building monitoring information can be monitored regularly in a targeted area; the building monitoring information includes building accessory monitoring parameters and environmental behavior monitoring parameters; The computing power collaboration unit includes edge nodes, regional servers, and the cloud: the edge nodes are equipped with a multimodal fusion module, the regional servers are equipped with a digital twin module, and the cloud is equipped with a prediction and optimization module; The multimodal fusion module is used to integrate building monitoring information: it builds a unified multi-source data model through semantic mapping and knowledge graph, obtains multi-source fusion standardized data, and transmits and shares data; The digital twin module is used to build a digital twin model: by monitoring parameters of building accessories, a three-dimensional dynamic digital twin model is built and data is updated in real time; The prediction and optimization module is used to establish a hybrid prediction model: it dynamically predicts building energy consumption and equipment operating status by integrating standardized data from multiple sources, and conducts coordinated control and optimization of the building energy system, thereby obtaining low-carbon building regulation optimization solutions and corresponding optimization control instructions; The control execution unit is used to receive optimization control instructions: through the optimization control instructions, the building's energy equipment and environmental conditioning equipment are controlled in real time, thereby making precise regional adjustments to the building's operating status; The user interaction unit is used for visual query and behavioral interaction: users query real-time building monitoring information and low-carbon building control optimization plans through a visual interface, and input personalized behavioral preferences to dynamically adjust user behavior data.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: This invention uses multi-source equipment in data acquisition units to achieve regional targeted and regular monitoring of parameters such as building structure, energy pipeline network, and user behavior. Through unified semantic standards and dynamic knowledge graphs, it achieves deep integration of cross-domain data such as building structure stability analysis and wind speed data, thereby improving the comprehensiveness and efficiency of data correlation analysis. The present invention constructs a three-level computing power collaboration system through computing power collaboration units. In this system, edge nodes are equipped with multimodal fusion modules to integrate building monitoring information. Regional servers are equipped with digital twin modules to perform complex simulations and accurately track energy transmission paths and equipment failure risks. The cloud is equipped with a prediction and optimization module for long-term regulation and management. This system builds an integrated management framework for the entire life cycle of the building cluster's macro-geographic environment, meso-level energy links, and micro-level equipment. This system enables cross-domain collaborative analysis and meets real-time requirements, as well as multi-objective optimization design that balances energy cost, energy efficiency, and comfort. This invention achieves precise regulation and low-carbon implementation by optimizing control instructions, and realizes human-computer interaction and dynamic adaptation through a visual interface, so as to achieve timely response to dynamic changes in the building environment and user behavior. It is data-driven throughout the entire cycle from building design to operation and maintenance, providing quantitative support for carbon footprint tracking and green building certification, and helping the construction industry to achieve carbon neutrality goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram showing the steps of the method flow of the present invention is shown; Figure 2 A connection diagram of the system modules of the present invention is shown. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0018] Example 1: like Figure 1-Figure 2As shown, a low-carbon building monitoring system based on digital twins includes a data acquisition unit, a computing power coordination unit, a control execution unit, and a user interaction unit. The data acquisition unit, computing power coordination unit, control execution unit, and user interaction unit are communicatively connected. The computing power coordination unit includes edge nodes, regional servers, and a cloud. The edge nodes are equipped with a multimodal fusion module, the regional servers are equipped with a digital twin module, and the cloud is equipped with a prediction and optimization module. The working steps are as follows: S1, the data acquisition unit collects building monitoring information: by setting the information collection cycle and marking the key nodes of the building, the building monitoring information is monitored regularly in a targeted manner; Building monitoring information includes building accessory monitoring parameters and environmental behavior monitoring parameters; Among them, building accessory monitoring parameters include building structure data, energy pipe network data and equipment operation data; environmental behavior monitoring parameters include environmental weather data and user behavior data; The building monitoring information is collected through multi-source sensor monitoring. The specific process is as follows: S1-1, building structure data includes basic geometric indicators, spatial relationship indicators, and complex shape indicators. Basic geometric indicators include the size, coordinate position, orientation angle, and cross-sectional shape of building components; spatial relationship indicators include the spacing, perpendicularity, parallelism, and spatial volume of building components; and complex shape indicators include the curvature radius and arc length of curved surfaces. Building structure data is collected using total stations, GPS monitors, and laser rangefinders. S1-2, energy network data includes network indicators and energy consumption indicators. Network indicators include pipeline flow and grid power; energy consumption indicators include electricity consumption, gas consumption, and water consumption. Energy network data is collected through flow meters, pressure gauges, electricity meters, water meters, and gas meters. S1-3, equipment operation data includes operation indicators and performance indicators; operation indicators include equipment start and stop status, operation time, and fault alarm frequency; performance indicators include equipment motor speed and equipment power factor; equipment power factor includes equipment voltage, current, and power; equipment operation data is collected through travel switches and power monitoring sensors; S1-4, environmental weather data includes environmental indicators and meteorological indicators; environmental indicators include light intensity and sunshine duration; meteorological indicators include temperature, humidity, wind speed, air pressure and rainfall; environmental weather data is collected through the API interface of the weather station; S1-5, user behavior data includes personnel activity indicators and energy preference indicators; among them, personnel activity indicators include pedestrian flow, area residence time and entrance and exit passage frequency; energy preference indicators include lighting switch time, air conditioning set temperature and usage period; user behavior data is collected through infrared sensors, smart sockets, air conditioning thermostats and user interaction units.

[0019] S2, the multimodal fusion module integrates building monitoring information: it builds a unified multi-source data model through semantic mapping and knowledge graph, obtains multi-source fusion standardized data, and transmits and shares data; S2-1, the specific process of pre-processing building monitoring information is as follows: Preprocessing of building structure data and equipment operation data: missing values ​​are processed by linear interpolation of adjacent data points, and outlier determination is performed using the 3σ principle; Preprocessing energy network data and environmental weather data: Build an LSTM neural network using historical data and time series to obtain predicted values. This is combined with the collected data to assess data deviations. Data deviation thresholds are then set and compared to identify outliers. Preprocessing user behavior data: Build an LSTM neural network based on historical data and time series data to obtain and mark the reasonable interval of user behavior data. When the detection value of the collected user behavior data exceeds the reasonable interval, it is determined to be an outlier. For data outliers identified in pre-processing, manual verification is performed to retest the data to correct the outliers and normalize the data to remove the dimension of the parameter indicators. Among them, normalization methods include Z-Score normalization and maximum-minimum value normalization.

[0020] S2-2, develop unified semantic standards by analyzing building monitoring information: Integrate building monitoring information with construction industry standards and international common data standards to develop a unified semantic vocabulary covering building accessory monitoring parameters and environmental behavior monitoring parameters; Among them, construction industry standards include BIM standards and energy management standards; international common data standards include JSON-LD and RDF data formats; For example, for the "basic geometric indicators-dimensions" in building structure data, the data format is uniformly stipulated as "length unit / meter + numerical value", and its unique identifier in the semantic system is clearly defined.

[0021] S2-3, establish semantic mapping rules by analyzing the semantic differences of multi-source sensors: Establish mapping rules from the semantics of sensor raw data to a unified semantic standard, thereby converting data into standard units; Taking "pipeline flow" in energy pipeline network data as an example, the data collected by different flow meters may have different units, such as cubic meters / hour and liters / minute. Through mapping rules, they are uniformly converted into standard units and associated with the corresponding concepts in the unified semantic vocabulary.

[0022] S2-4, set and mark the knowledge graph entities and the relationships between them, build the knowledge graph and update it dynamically: Knowledge graph entities include building structures, energy networks, equipment, environment, and users; The relationships between entities include connection relationships, usage relationships, and impact relationships; For example, there is a connection relationship between equipment and energy pipe networks, a usage relationship between users and equipment, and an impact relationship between the environment and building structures; Through natural language processing (NLP) technology and machine learning algorithms, entities and relationships are extracted from the collected building monitoring information to build a knowledge graph; For structured data, such as equipment operation data, entities and relationships are directly extracted through data parsing; for unstructured data, such as user behavior data, NLP technologies such as named entity recognition and relationship extraction are used for processing, and the extracted information is added to the knowledge graph. Establish a dynamic update mechanism for the knowledge graph. With the real-time collection of building monitoring information and the addition of new data, automatically update the entities and relationships in the knowledge graph. Regularly check and optimize the knowledge graph for consistency to ensure the accuracy and completeness of the graph.

[0023] S2-5, then perform spatiotemporal alignment by aligning timestamps with unified geographic coordinates to obtain multi-source fused standardized data; It should be noted that by integrating the semantics of multiple fields such as building structure, energy management, environmental monitoring, and user behavior, and by building unified semantic standards and mapping rules, the semantic barriers of data in different fields can be broken down, and the deep integration of multi-source data at the semantic level can be achieved; For example, combining the stability analysis of building structures with wind speed and rainfall in environmental weather data through semantic fusion can more accurately assess the impact of extreme weather on building structures and provide more comprehensive data support for building safety warnings. By introducing a dynamic knowledge graph as the core framework for data integration, the complex relationships between various elements in the building system and their dynamic changes are reflected in real time. Through knowledge extraction and graph update mechanisms, when building equipment fails, user behavior patterns change, or environmental parameters fluctuate, the knowledge graph is quickly updated, ensuring that the data model always maintains an accurate description of the building's operating status. This dynamic nature provides a more flexible and intelligent data foundation for intelligent building management. For example, real-time relationship analysis based on knowledge graphs can promptly identify the chain reaction of equipment failures on energy consumption and user experience, thereby enabling more accurate fault diagnosis and optimized decision-making. The multi-source unified data model built on the knowledge graph has powerful multi-dimensional data correlation analysis capabilities. It can not only perform vertical analysis of the same type of data, such as historical trend analysis of equipment operation data, but also horizontal correlation analysis of different types of data, such as correlation analysis between user behavior data and energy consumption data. By exploring the potential causal relationships and correlation patterns between data, we can provide deeper insights for building energy-saving optimization, user service improvement, facility maintenance management, etc. For example, by analyzing the relationship between users' energy preferences and environmental weather data in different time periods, we can optimize the operation strategy of the air-conditioning system, thereby reducing energy consumption while meeting user comfort.

[0024] S3, the digital twin module is used to build a digital twin model: by monitoring parameters of building accessories, a three-dimensional dynamic digital twin model is built and data is updated in real time; A multi-scale, full-life cycle management mechanism is established for building clusters, including macro, meso, and micro scales. The specific process is as follows: S3-1, macro-scale is constructed by integrating three-dimensional geographic information system (3D-GIS) and building information model (BIM). Environmental weather data is input through 3D-GIS to build a macro spatial framework of the building's geographical location and surrounding environment, and building structure data is input through BIM to mark the building structure zoning; S3-2, at the mesoscale, uses energy network data to build digital links between equipment, networks, and energy consumption. This connects building floor equipment with the energy network and labels all equipment and networks, allowing for real-time tracking of energy transmission paths and calculation of losses. S3-3, at the micro scale, the internal structure of the equipment is modeled and the equipment operation data is input to predict the probability of equipment failure, and then the risk level of the equipment is determined and a corresponding risk warning signal is generated.

[0025] S4, the prediction and optimization module establishes a hybrid prediction model: it dynamically predicts building energy consumption and equipment operating status by integrating standardized data from multiple sources, and conducts coordinated control and optimization of the building energy system, thereby obtaining low-carbon building regulation optimization solutions and corresponding optimization control instructions; S4-1, dynamically predict building energy consumption and equipment operating status through multi-source fusion of standardized data; Extract building geometric features G from building structure data. Building geometric features G include basic geometric indicators and spatial relationship indicators. Building geometric features are used to analyze the long-term impact on energy distribution status. Dynamic topology features T(t) are extracted from energy network data and equipment operation data. Dynamic topology features T(t) include network indicators, energy consumption indicators, operation indicators, and performance indicators. Dynamic topology features T(t) are used to dynamically reflect energy transmission paths in real time. Through the historical data analysis and linear regression fitting, the weight factors of dynamic topological features T(t) and building geometric features G are obtained and marked as 、 ; Then, the dynamic space-energy coupling feature vector is obtained by weighted synthesis of the dynamic topological feature T(t) and the building geometric feature G and its corresponding weight factors. : .

[0026] S4-2, extracting environmental time series features E(t) through environmental weather data. Environmental time series features E(t) include environmental indicators and meteorological indicators. Environmental time series features E(t) are real-time fluctuation data. User behavior features B(t) are extracted from user behavior data. User behavior features B(t) include energy preference indicators and are periodic pattern data. Through semantic mapping, historical behaviors in the building are classified and a behavior cluster center Ck is constructed to distinguish the behavior patterns of the building, including office mode and residential mode. The number of behavior patterns is marked as K, and any behavior pattern is marked as k. Obtain the behavior alignment function through the knowledge graph and mark it as Align, which is used to associate and match environmental fluctuations with similar behavior patterns. For example, linking temperature fluctuations in office mode with air conditioning equipment. By calculating the energy consumption fluctuation variance of the building under different behavior modes, the behavior mode weight is set And assign values: when the energy consumption fluctuation variance is higher, the weight assigned to the behavior pattern is higher; The wavelet transform function WT is used to decompose the environmental time series features E(t) into multi-scale time series, and combined with the user behavior features B(t), behavior cluster center Ck, behavior alignment function Align, behavior pattern weight , thereby obtaining the multi-scale time series-behavior feature fusion vector : .

[0027] S4-3, the dynamic space-energy coupling eigenvector and multi-scale temporal-behavioral feature fusion vector Perform splicing and obtain splicing feature vector , and perform time series prediction through the LSTM deep learning model to obtain the prediction output vector : ; By combining static physical properties and dynamic environmental behaviors, the building energy consumption is jointly affected to achieve dynamic prediction of building energy consumption level and equipment operating status.

[0028] S4-4, then conduct collaborative control and optimization of the building energy system to obtain a low-carbon building regulation optimization plan and corresponding optimization control instructions; Set the equipment control instruction U as the action space to regulate the building equipment, such as air conditioning equipment and lighting equipment; The energy cost coefficient C(U) is obtained by combining the energy consumption of the equipment with the unit price of electricity, and by combining the network flow with the unit price of energy. The energy efficiency index coefficient E (U) is obtained through the user comfort contribution per unit energy consumption; User comfort refers to the duration of use of air conditioning and lighting within the comfort zone. The center value of the comfort zone is set by the average of the temperature, humidity, and brightness perceived by the user, and the floating range is preset to obtain the comfort zone of each device. The comfort deviation coefficient D(U) is obtained by calculating the deviation between the actual comfort data value and the comfort range. For example, the temperature deviation is obtained by calculating the deviation difference between the actual temperature value and the temperature comfort range. Similarly, the deviation of humidity and brightness is obtained, and the comfort deviation coefficient D(U) is obtained by weighted summation. Then, the weight coefficients of the energy cost coefficient C(U), the energy efficiency index coefficient E(U) and the comfort deviation coefficient D(U) are set to output the multi-objective optimization function: ; Among them, λ1, λ2, and λ3 are the weight coefficients of the energy cost coefficient C(U), the energy efficiency index coefficient E(U), and the comfort deviation coefficient D(U), respectively. When the energy cost coefficient C(U) is lower, the energy efficiency index coefficient E(U) is higher, and the comfort deviation coefficient D(U) is lower, the multi-objective optimization function is lower.

[0029] S4-5, when the multi-objective optimization function takes the minimum value, the corresponding equipment control instruction U is the optimization control instruction of the low-carbon building regulation optimization solution; In addition, to ensure the feasibility of the device control command U, collaborative control constraints are set, including upper and lower limits of device physical parameters, minimum comfort constraints, and grid power limits. This allows multi-objective performance optimization to be achieved under the conditions of normal equipment, normal grid conditions, and user comfort, balancing comfort, energy efficiency, and cost. Through the digital twin model, macro, meso and micro scales are divided, so that multi-objective optimization can be carried out for different scales, and corresponding data indicators are selected for analysis to generate low-carbon building control optimization plans corresponding to each scale.

[0030] S5, the control execution unit receives the optimization control instructions: through the optimization control instructions, the building's energy equipment and environmental adjustment equipment are controlled in real time, thereby making precise regional adjustments to the building's operating status to achieve the demand goals of low-carbon buildings.

[0031] S6, the user interaction unit performs visual query and behavioral interaction: users query real-time building monitoring information and low-carbon building control optimization plans through the visual interface, and input personalized behavioral preferences to dynamically adjust user behavior data.

[0032] In summary, the present invention uses multi-source data acquisition units to achieve regional targeted and timed monitoring of parameters such as building structure, energy pipeline network, and user behavior. Through unified semantic standards and dynamic knowledge graphs, it achieves deep integration of cross-domain data such as building structure stability analysis and wind speed data, thereby improving the comprehensiveness and efficiency of data correlation analysis. The present invention constructs a three-level computing power collaboration system through computing power collaboration units. In this system, edge nodes are equipped with multimodal fusion modules to integrate building monitoring information. Regional servers are equipped with digital twin modules to perform complex simulations and accurately track energy transmission paths and equipment failure risks. The cloud is equipped with a prediction and optimization module for long-term regulation and management. This system builds an integrated management framework for the entire life cycle of the building cluster's macro-geographic environment, meso-level energy links, and micro-level equipment. This system enables cross-domain collaborative analysis and meets real-time requirements, as well as multi-objective optimization design that balances energy cost, energy efficiency, and comfort. This invention achieves precise regulation and low-carbon implementation by optimizing control instructions, and realizes human-computer interaction and dynamic adaptation through a visual interface, so as to achieve timely response to dynamic changes in the building environment and user behavior. It is data-driven throughout the entire cycle from building design to operation and maintenance, providing quantitative support for carbon footprint tracking and green building certification, and helping the construction industry to achieve carbon neutrality goals.

[0033] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0034] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0035] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A low-carbon building monitoring method based on digital twins, characterized by: The following steps are involved: Step 1: Collect building monitoring information: By setting the information collection cycle and marking the key nodes of the building, the building monitoring information can be monitored regularly in a targeted manner. The building monitoring information includes building accessory monitoring parameters and environmental behavior monitoring parameters. Step 2: Integrate building monitoring information: Build a multi-source unified data model through semantic mapping and knowledge graph, obtain multi-source fusion standardized data, and transmit and share data; Step 3: Build a digital twin model: Build a three-dimensional dynamic digital twin model through building accessory monitoring parameters, and update the data in real time; Step 4: Establish a hybrid prediction model: Dynamically predict building energy consumption and equipment operating status by integrating standardized data from multiple sources, and conduct coordinated control and optimization of the building energy system to obtain low-carbon building regulation optimization solutions and corresponding optimization control instructions; Step 5: Receive optimization control instructions: Use optimization control instructions to control the building's energy equipment and environmental conditioning equipment in real time, thereby accurately adjusting the building's operating status in different regions; Step 6: Visual query and behavioral interaction: Users use the visual interface to query building monitoring information and low-carbon building control optimization plans in real time, and input personalized behavioral preferences to dynamically adjust user behavior data.

2. A low-carbon building monitoring method based on digital twins according to claim 1, characterized in that: The specific process of collecting building monitoring information is as follows: Building accessory monitoring parameters include building structure data, energy network data, and equipment operation data; Environmental behavior monitoring parameters include environmental weather data and user behavior data; Collect building monitoring information through multi-source sensor monitoring; Building structure data includes basic geometric indicators, spatial relationship indicators, and complex shape indicators; energy network data includes network indicators and energy consumption indicators; equipment operation data includes operation indicators and performance indicators; Environmental weather data includes environmental indicators and meteorological indicators; user behavior data includes personnel activity indicators and energy preference indicators.

3. A low-carbon building monitoring method based on digital twins according to claim 2, characterized in that: The specific process of integrating building monitoring information is as follows: S2-1, the specific process of pre-processing building monitoring information is as follows: Preprocessing of building structure data and equipment operation data: missing values ​​are processed by linear interpolation of adjacent data points, and outlier determination is performed using the 3σ principle; Preprocessing energy network data and environmental weather data: Build an LSTM neural network using historical data and time series to obtain predicted values. This is combined with the collected data to assess data deviations. Data deviation thresholds are then set and compared to identify outliers. Preprocessing user behavior data: Build an LSTM neural network using historical data and time series data to obtain and mark the reasonable intervals of user behavior data. When the detection value of the collected user behavior data exceeds the reasonable interval, it is determined to be an outlier. For data outliers identified in pre-processing, manual verification is performed to retest the data to correct the outliers and normalize the data to remove the dimension of the parameter indicators. S2-2, develop unified semantic standards by analyzing building monitoring information: Integrate building monitoring information with construction industry standards and international common data standards to develop a unified semantic vocabulary covering building accessory monitoring parameters and environmental behavior monitoring parameters; S2-3, establish semantic mapping rules by analyzing the semantic differences of multi-source sensors: Establish mapping rules from the semantics of sensor raw data to a unified semantic standard, thereby converting data into standard units; S2-4, set and mark the knowledge graph entities and the relationships between them, build the knowledge graph and update it dynamically: Knowledge graph entities include building structures, energy networks, equipment, environment, and users; relationships between entities include connection relationships, usage relationships, and impact relationships; Through natural language processing (NLP) technology and machine learning algorithms, entities and relationships are extracted from the collected building monitoring information to build a knowledge graph; Establish a dynamic update mechanism for the knowledge graph and regularly check and optimize the knowledge graph for consistency; S2-5, then perform spatiotemporal alignment by aligning timestamps with unified geographic coordinates to obtain multi-source fused standardized data.

4. A low-carbon building monitoring method based on digital twins according to claim 3, characterized in that: The specific process of building a digital twin model is as follows: Establish a multi-scale, full-life cycle management mechanism for building clusters, including macro-scale, meso-scale and micro-scale; The macro-scale is constructed by integrating the 3D geographic information system and the building information model. Environmental weather data is input through 3D-GIS to build a macro spatial framework of the building's geographical location and surrounding environment. The building structure data is input through BIM to mark the building structure zoning. At the mesoscale, energy network data is used to build digital links between equipment, networks, and energy consumption. This connects building floor equipment with the energy network and labels all equipment and networks, allowing for real-time tracking of energy transmission paths and calculation of losses. At the micro scale, the internal structure of the equipment is modeled and the equipment operation data is input to predict the probability of equipment failure, and then the risk level of the equipment is determined and a corresponding risk warning signal is generated.

5. A low-carbon building monitoring method based on digital twins according to claim 4, characterized in that: The specific process of establishing a hybrid prediction model is as follows: Dynamically predict building energy consumption and equipment operating status through multi-source fusion of standardized data; Analyze and obtain dynamic space-energy coupling feature vectors through building structure data, energy network data and equipment operation data ; Analyze and obtain multi-scale time series-behavior feature fusion vectors through environmental weather data and user behavior data ; The dynamic space-energy coupling eigenvector and multi-scale temporal-behavioral feature fusion vector Perform splicing and obtain splicing feature vector , and perform time series prediction through the LSTM deep learning model to obtain the prediction output vector .

6. A low-carbon building monitoring method based on digital twins according to claim 5, characterized in that: Obtaining dynamic space-energy coupling eigenvectors The specific process is: Dynamically predict building energy consumption and equipment operating status through multi-source fusion of standardized data; Extract building geometric features G through building structure data, and extract dynamic topological features T(t) through energy network data and equipment operation data; Through the historical data analysis and linear regression fitting, the weight factors of dynamic topological features T(t) and building geometric features G are obtained and marked as 、 ; Then, the dynamic space-energy coupling feature vector is obtained by weighted synthesis of the dynamic topological feature T(t) and the building geometric feature G and its corresponding weight factors. .

7. The low-carbon building monitoring method based on digital twin according to claim 6 is characterized in that: Obtain multi-scale time series-behavior feature fusion vector The specific process is: Extract environmental time series features E(t) through environmental weather data, and extract user behavior features B(t) through user behavior data; Construct the behavior cluster center Ck through semantic mapping, mark the number of behavior patterns as K, mark any behavior pattern as k, obtain the behavior alignment function through the knowledge graph and mark it as Align; By calculating the energy consumption fluctuation variance of the building under different behavior modes, the behavior mode weight is set ; The wavelet transform function WT is used to decompose the environmental time series features E(t) into multi-scale time series, and combined with the user behavior features B(t), behavior cluster center Ck, behavior alignment function Align, behavior pattern weight , thereby obtaining the multi-scale time series-behavior feature fusion vector .

8. The low-carbon building monitoring method based on digital twin according to claim 7 is characterized in that: The specific process of obtaining the low-carbon building regulation optimization plan and the corresponding optimization control instructions is as follows: Set the equipment control instruction U as the action space to regulate the equipment of the building; The energy cost coefficient C(U) is obtained by combining the energy consumption of the equipment with the unit price of electricity, and the network flow rate with the unit price of energy. The energy efficiency index coefficient E(U) is obtained by the user comfort contribution per unit energy consumption. The comfort deviation coefficient D(U) is obtained by the deviation between the actual comfort data value and the comfort range. Then, the weight coefficients of the energy cost coefficient C(U), the energy efficiency index coefficient E(U) and the comfort deviation coefficient D(U) are set to output the multi-objective optimization function; By taking the minimum value of the multi-objective optimization function, the corresponding equipment control instruction U is the optimization control instruction of the low-carbon building regulation optimization solution.

9. A low-carbon building monitoring system based on digital twins, characterized by: The system comprises a data acquisition unit, a computing power coordination unit, a control execution unit and a user interaction unit, wherein the data acquisition unit, the computing power coordination unit, the control execution unit and the user interaction unit are communicatively connected to each other, and the system executes a low-carbon building monitoring method based on digital twins as described in any one of claims 1 to 8 above; The data acquisition unit is used to collect building monitoring information: by setting the information collection cycle and marking the key nodes of the building, the building monitoring information can be monitored regularly in a targeted manner. Building monitoring information includes building accessory monitoring parameters and environmental behavior monitoring parameters; The computing power collaboration unit includes edge nodes, regional servers, and the cloud: the edge nodes are equipped with a multimodal fusion module, the regional servers are equipped with a digital twin module, and the cloud is equipped with a prediction and optimization module; The multimodal fusion module is used to integrate building monitoring information: it builds a unified multi-source data model through semantic mapping and knowledge graph, obtains multi-source fusion standardized data, and transmits and shares data; The digital twin module is used to build a digital twin model: by monitoring parameters of building accessories, a three-dimensional dynamic digital twin model is built and data is updated in real time; The prediction and optimization module is used to establish a hybrid prediction model: it dynamically predicts building energy consumption and equipment operating status by integrating standardized data from multiple sources, and conducts coordinated control and optimization of the building energy system, thereby obtaining low-carbon building regulation optimization solutions and corresponding optimization control instructions; The control execution unit is used to receive optimization control instructions: through the optimization control instructions, the building's energy equipment and environmental conditioning equipment are controlled in real time, thereby making precise regional adjustments to the building's operating status; The user interaction unit is used for visual query and behavioral interaction: users query real-time building monitoring information and low-carbon building control optimization plans through a visual interface, and input personalized behavioral preferences to dynamically adjust user behavior data.

Images