A method and related device for dynamically evaluating building carbon emissions
By extracting features from building BIM models and inputting data into pre-built machine learning models, the problems of result bias and complexity and time consumption in existing building carbon emission assessment methods are solved, achieving more accurate and efficient dynamic carbon emission assessment and supporting building carbon emission reduction decisions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-08
- Publication Date
- 2026-06-23
AI Technical Summary
Existing methods for assessing carbon emissions throughout the building life cycle suffer from significant biases in assessment results and are complex and time-consuming processes. Static assessment methods assume that building energy use is static, leading to biases, while dynamic assessment methods do not consider dynamic variables such as weather and building thermal performance.
By acquiring the building BIM model, extracting feature data and inputting it into a pre-built building energy consumption prediction model, a machine learning model containing prototype building model data, future meteorological feature data, resident energy consumption behavior data and building supply-side dynamic energy model is used to conduct dynamic assessment of carbon emissions, taking into account dynamic changes throughout the building's entire life cycle.
It enables more accurate carbon emission assessments, reduces the complexity and time of the assessment process, provides more convenient decision-making tools, and offers more precise carbon reduction support for building planning, design, and optimization.
Smart Images
Figure CN122264629A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of carbon emission prediction technology, and specifically relates to a method and related apparatus for dynamic assessment of building carbon emissions. Background Technology
[0002] According to statistics, about 28% of total energy-related carbon dioxide emissions come from the consumption of energy or other resources during the design, operation and demolition phases of buildings. Therefore, achieving a building carbon emission assessment from a life-cycle perspective is crucial for decision-making in building planning, design and optimization. Secondly, assessing the carbon emissions of buildings throughout their life cycle is an important basis for seeking carbon reduction potential and pathways.
[0003] Currently, existing methods for assessing building lifecycle carbon emissions include static and dynamic assessments, both of which suffer from significant biases in the results and are complex and time-consuming processes. Specifically, existing static assessment methods primarily define the boundaries of the building's lifecycle carbon emission system and calculate static energy consumption based on equivalent days (assuming consistent daily carbon emissions), thereby determining the building's carbon emission range and intensity. Since the accuracy of lifecycle carbon emission assessments depends on the building's dynamic changes in time and space, and existing static assessment methods typically assume that energy use and energy mix are static during the building's lifecycle, the assessment results deviate significantly from actual carbon emissions. Existing dynamic assessment methods typically use dynamic energy simulations from building performance design, using estimated or measured annual energy usage as a point value for a given year. They do not consider changes in dynamic variables such as weather and building thermal performance throughout the building's lifecycle, leading to significant biases in the results. Furthermore, existing dynamic assessment methods generally require manual parameter input and the use of specialized building energy consumption simulation software, making the assessment process complex, time-consuming, and requiring substantial time and effort. Summary of the Invention
[0004] To address the technical problems existing in the prior art, this invention provides a method and related apparatus for dynamic assessment of building carbon emissions, in order to solve the technical problems that existing methods for assessing carbon emissions throughout the building's life cycle, including static and dynamic assessment methods, generally suffer from large deviations in assessment results and complex and time-consuming processes.
[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: This invention provides a method for dynamic assessment of building carbon emissions, comprising: Obtain the BIM model of the building to be evaluated; Feature extraction is performed on the BIM model of the building to be evaluated to obtain the building feature data of the building to be evaluated; The building characteristic data of the building to be evaluated is input into the pre-built building energy consumption prediction model to obtain the energy consumption prediction data of the building to be evaluated. The pre-built building energy consumption model is a machine learning model pre-trained using a pre-built building life cycle carbon emission database. The pre-built building life cycle carbon emission database includes prototype building model data, future meteorological characteristic data of the prototype building location, energy consumption behavior data of residents in the prototype building location, and building supply-side dynamic energy model. Based on the energy consumption prediction data of the building to be evaluated, the dynamic assessment results of the building's carbon emissions are obtained.
[0006] Furthermore, the architectural feature data of the building to be evaluated includes the building's spatial geometric parameters, thermal properties of the building envelope, and material properties; the architectural feature data of the building to be evaluated is saved in the form of a Word document.
[0007] Furthermore, the process of generating prototype building model data includes: The design drawings of several existing buildings are analyzed to obtain statistical data on existing buildings; the statistical data on existing buildings includes the basic structural parameters and spatial distribution parameters of existing buildings. Clustering and identification of existing building statistics, and deriving the spatial distribution characteristics of typical prototype buildings through the auxiliary averaging method, thus obtaining a typical prototype building model; Based on predetermined building design standards, the Latin hypercube sampling method is used to generate building models with different window-to-wall ratios, thermal properties of the building envelope, and energy consumption behavior data, thus obtaining prototype building model data.
[0008] Furthermore, the process of generating future meteorological characteristic data for the location of the prototype building includes: Obtain typical annual meteorological data and actual annual meteorological data for the location of existing buildings; Hourly statistical analysis was conducted on typical annual meteorological data and actual annual meteorological data of the location of the existing building to obtain hourly baseline values of meteorological parameters for the existing building. Based on the hourly reference values of meteorological parameters of existing buildings, meteorological forecast values with a monthly time scale are generated using the HadCM3 climate model and the A2 scenario method. Based on the Morphing principle, the hourly reference values of meteorological parameters of existing buildings are fused with meteorological forecast values on a monthly time scale to obtain future meteorological characteristic data of the prototype building's location.
[0009] Furthermore, the process of generating energy consumption behavior data for the resident site of the prototype building includes: Based on the demographic data of the location of the existing building and combined with the spatial distribution characteristics of the prototype building, the demographic characteristics of the residents of the existing building are generated. Based on the population characteristics of residents in existing buildings and the energy consumption characteristics of residents in the location of existing buildings, energy consumption behavior data of residents is randomly generated to obtain energy consumption behavior data of residents in the location of the prototype building.
[0010] Furthermore, the dynamic energy model for the building supply side includes wind power generation model, photovoltaic power generation model, hydrogen electrolyzer model, hydrogen storage tank model, battery model, fuel cell model, combined heat and power model, solar collector model, electric chiller model, gas boiler model, absorption chiller model, and thermal storage tank / cold storage tank model.
[0011] Furthermore, the process of obtaining the dynamic assessment results of the carbon emissions of the building to be assessed based on the energy consumption prediction data of the building to be assessed includes: Based on the geographical location information of the building to be evaluated and the evaluation time period information, determine the carbon emission factors corresponding to different energy sources; Based on the carbon emission factors corresponding to different energy sources and the energy consumption prediction data of the building to be evaluated, the dynamic assessment results of the carbon emissions of the building to be evaluated are calculated.
[0012] The present invention also provides a dynamic assessment system for building carbon emissions, comprising: The model acquisition module is used to acquire the BIM model of the building to be evaluated. The feature extraction module is used to extract features from the BIM model of the building to be evaluated, and obtain the building feature data of the building to be evaluated. The energy consumption prediction module is used to input the building characteristic data of the building to be evaluated into the pre-built building energy consumption prediction model to obtain the energy consumption prediction data of the building to be evaluated. The pre-built building energy consumption model is a machine learning model pre-trained using a pre-built building life cycle carbon emission database. The pre-built building life cycle carbon emission database includes prototype building model data, future meteorological characteristic data of the prototype building location, energy consumption behavior data of residents in the prototype building location, and a building supply-side dynamic energy model. The dynamic assessment module is used to obtain the dynamic assessment results of the carbon emissions of the building to be assessed based on the energy consumption prediction data of the building.
[0013] The present invention also provides an electronic device, comprising: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, performs the aforementioned method for dynamic assessment of building carbon emissions.
[0014] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for dynamic assessment of building carbon emissions.
[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a dynamic assessment method for building carbon emissions. This method acquires the BIM model of the building to be assessed and extracts its feature data. This data is then input into a pre-trained machine learning model using a building lifecycle carbon emission database containing prototype building model data, future meteorological characteristic data, resident energy consumption behavior data, and a building supply-side dynamic energy model. This database generates energy consumption prediction data, leading to a dynamic carbon emission assessment result. This method fully considers the dynamic changes of different influencing factors in building carbon emission assessment, making the assessment results more consistent with actual changes and achieving a more accurate assessment of building carbon emissions. Compared to existing static assessment methods, this method fully considers the spatiotemporal dynamic changes of buildings, avoiding assessment biases caused by assumptions about building energy use and static combinations. Furthermore, compared to existing dynamic assessment methods, this method not only considers the changes of dynamic variables such as weather and building thermal performance throughout the building's lifecycle, ensuring that the assessment results are more consistent with actual changes, but also eliminates the need for manually inputting numerous parameters and using professional building energy consumption simulation software, making the assessment process simpler and less time-consuming. This invention can provide more accurate basis for decision-making in building planning, design, and optimization processes, and can provide strong support for seeking carbon reduction potential and pathways.
[0016] The building carbon emission dynamic assessment system, electronic device, and computer-readable storage medium provided by this invention possess all the advantages of the aforementioned building carbon emission dynamic assessment methods. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 A flowchart of the building carbon emission dynamic assessment method provided in Example 1; Figure 2 This is a schematic diagram illustrating the process of generating prototype building data in Example 1. Figure 3 This is a schematic diagram illustrating the process of generating future meteorological characteristic data for the location of the prototype building in Example 1. Figure 4This is a schematic diagram illustrating the process of generating energy consumption behavior data of residents at the location of the prototype building in Example 1. Figure 5 This is a structural block diagram of the building carbon emission dynamic assessment system provided in Example 2; Figure 6 This is a structural block diagram of the electronic device provided in Example 3. Detailed Implementation
[0019] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0020] This invention provides a method for dynamic assessment of building carbon emissions, comprising the following steps: Step 100: Obtain the BIM model of the building to be evaluated.
[0021] Step 200: Extract features from the BIM model of the building to be evaluated to obtain the building feature data.
[0022] Step 300: Input the building characteristic data of the building to be evaluated into the pre-built building energy consumption prediction model to obtain the energy consumption prediction data of the building to be evaluated; wherein, the pre-built building energy consumption model is a machine learning model pre-trained using the pre-built building life cycle carbon emission database; the pre-built building life cycle carbon emission database includes prototype building model data, future meteorological characteristic data of the prototype building location, energy consumption behavior data of residents in the prototype building location, and building supply-side dynamic energy model.
[0023] Step 400: Based on the energy consumption prediction data of the building to be evaluated, obtain the dynamic assessment results of the carbon emissions of the building to be evaluated.
[0024] In the above implementation, a building carbon emission database covering the entire building lifecycle is constructed. This database includes prototype building model data, future meteorological characteristics data of the prototype building's location, energy consumption behavior data of residents in the prototype building's location, and a dynamic energy model of the building's supply side. A machine learning model trained on this database is used as a building energy consumption prediction model. This fully considers the dynamic changes of different influencing factors in building carbon emission assessment, such as the degradation of the thermal properties of external wall insulation materials throughout the entire operating cycle. This makes the assessment results more consistent with actual changes, thus more accurately assessing building carbon emissions. Furthermore, the inclusion of future meteorological characteristics data, resident energy consumption behavior data, and the dynamic energy model of the building's supply side in the database incorporates various dynamic variables throughout the building's lifecycle, providing a more comprehensive reflection of carbon emissions at different stages. This avoids the biases in assessment results caused by traditional dynamic assessment methods that fail to consider changes in dynamic variables, thereby improving the accuracy of the assessment.
[0025] In this invention, only the building feature information of the building to be evaluated needs to be extracted, and then the building feature data of the building to be evaluated is input into a pre-built building energy consumption prediction model. By comparing the feature information with the prototype building data in the database, the predicted energy consumption of the building to be evaluated can be obtained, thereby quickly assessing dynamic carbon emissions. There is no need to manually input a large number of parameters, reducing the tediousness of manual operation and improving the evaluation efficiency. In addition, this invention is based on a database and machine learning model, which has stronger versatility and adaptability. It can conduct dynamic carbon emission assessments for different types of buildings, providing a more convenient and efficient tool for decision-making in the building planning, design and optimization process, and helping to promote the practice and application of carbon emission reduction in the construction industry.
[0026] The following specific embodiments further explain the building carbon emission dynamic assessment method provided by the present invention: Example 1 As attached Figure 1 As shown, this embodiment 1 provides a method for dynamic assessment of building carbon emissions, including the following steps: Step 1: Obtain the BIM model of the building to be evaluated. The BIM model of the building to be evaluated should be in gbXML format. It should be noted that gbXML (Green Building XML, a file format based on Extensible Markup Language) is specifically used for data exchange between Building Information Modeling (BIM) and Building Performance Analysis (BPA), and is widely used in green building design, building performance simulation, and environmental sustainability assessment. Compared to IFC (Industry Foundation Classes, a standardized digital model used for data exchange and sharing in the field of architecture, engineering, and construction (AEC), gbXML supports scanned volumes, constructs solid geometry, and boundary representations, and only accepts structures represented by boundary loops, thus limiting its ability to represent space using boundary representations. Exporting the BIM model of the building to be evaluated using gbXML ensures that data is transferred from the BIM model to the building energy model, and its data structure includes geometric and semantic information compatible with simulation engines.
[0027] Step 2: Extract features from the BIM model of the building to be evaluated to obtain its architectural feature data. This architectural feature data includes the building's spatial geometric parameters, thermal properties of the building envelope, and material properties. Preferably, the architectural feature data is saved as a Word document.
[0028] The specific process is as follows: Using a pre-written Python script, features are extracted from the BIM model of the building to be evaluated to obtain architectural feature data. The pre-written Python script uses XML parsing technology to read the structured data of the BIM model of the building to be evaluated, which is output in gbXML format, and queries the pre-defined building components, such as exterior walls, roof, shading structure, windows, window-to-wall ratio, and floor height, through namespaces to obtain the architectural feature data of the building to be evaluated.
[0029] For example, for the exterior walls, roofs, and shading structures of a building, a pre-written Python script is used to locate the surface elements of the exterior walls, roofs, or shading structures. Based on the constructed material layer information such as thickness and thermal conductivity, the thermal performance index U-value (total thermal resistance plus the reciprocal of a fixed value) is calculated, and the absorptivity and detailed material layer data are extracted. The calculation process of the thermal performance index U-value is as follows:
[0030]
[0031] in, The total thermal resistance of the building envelope; The internal surface thermal resistance is set to a fixed value of 0.13m in EnergyPlus. 2 K / W; The number of material layers; For the first The thickness of the layer material, in meters; For the first Thermal conductivity of the layer material, W / mK; The external surface thermal resistance is set to a fixed value of 0.04m in EnergyPlus. 2 K / W.
[0032] For windows, a pre-written Python script identifies operable windows and extracts their U-value, solar heat gain coefficient (including values for different incident angles), and absorptivity. The window-to-wall ratio is calculated by extracting the geometric dimensions (width and height) of the exterior walls and windows, and then allocating the data to the four directions (north, east, south, and west) based on the azimuth angle, thus obtaining the ratio of window area to exterior wall area in each direction. Floor height is calculated by the difference in floor elevation values, retaining accuracy to one decimal place. The extracted features are finally formatted and saved to a Word document, clearly presenting thermal performance, geometric information, and material properties. Users select input files and output paths through a graphical interface, and the pre-written Python script automatically completes the process from parsing and calculation to saving, ensuring fault tolerance through error prompts. The entire method is modular and highly automated, making it suitable for building energy consumption analysis or green building design.
[0033] The spatial geometric parameters of the building to be evaluated include the building area, number of floors, floor height, window-to-wall ratio, area ratio of each functional area on each floor, and thermal property data of the building envelope, including the type, thickness, and thermal conductivity of each layer of exterior wall material, the type, thickness, and thermal conductivity of each layer of roof material, the type, thickness, and thermal conductivity of each layer of floor slab material, and the heat transfer coefficient, SHGC value, and VT value of exterior windows.
[0034] In this embodiment 1, after exporting the BIM model of the building to be estimated into gbXML data format, a Python script is used to extract the building feature data from the gbXML file. Specifically, features such as exterior walls, roof, shading structure, windows, window-to-wall ratio, and floor height of the building information model are extracted by parsing the gbXML file. Among them, lxml.etree and xml.etree.ElementTree are used to parse the XML file, obtain the root node, and define namespaces to correctly query tags.
[0035] In feature extraction, the script uses the `extract_info` function to locate the exterior walls, roof, and shading structure. It associates these with `constructionIdRef` elements, then uses `layerIdRef` and `materialIdRef` to extract the thickness and thermal conductivity of the material layers, calculates the U-value (total thermal resistance plus the reciprocal of 0.17), and obtains the absorptivity and detailed material layer information. For exterior windows, the script locates the `OperableWindow`, extracts the U-value, solar heat gain coefficient (SHGC, including the angle of incidence), and absorptivity. The window-to-wall ratio and floor height are calculated using the `calculate_wwr_and_floor_heights` function. The window-to-wall ratio is calculated for each direction using the width and height in the `RectangularGeometry` of the exterior walls and windows, combined with the azimuth angle (Azimuth) assigned to the north, east, south, and west directions. The floor height is calculated using the difference in the `Level` values of the `BuildingStorey`.
[0036] Auxiliary functions such as `calculate_u_value`, `find_layers`, `find_layers_details`, and `find_absorptance` calculate the U-value, locate material layers, obtain layer details, and extract the absorptance, respectively. The extracted results are saved to a Word document via `python-docx`, including formatted window-to-wall ratios, floor heights, and component information. For user interaction, tkinter provides a GUI that allows selecting the gbXML file and output Word file path via a filedialog, and displays success or error messages using a messagebox. The entire process is automated, from parsing XML, querying related attributes, calculating derived features, to formatted output, combining modularity and fault tolerance, making it suitable for building energy consumption analysis or green building design scenarios.
[0037] The code is encapsulated into a script to automatically extract relevant features from BIM building files. For a target building, simply export the BIM model as a gbXML file, then import it into the feature extraction script. The script will automatically extract key feature information such as geometric information and thermal properties of the building envelope, and output it as a Word document. This automated feature extraction method avoids the complexity of manually searching for and obtaining building feature information from the BIM model, significantly reducing the workload of information acquisition, conversion, and input, and effectively improving the efficiency of building energy consumption analysis. After obtaining the feature data of the building to be evaluated, it is imported into the trained building energy consumption prediction model to calculate the energy consumption.
[0038] Step 3: Input the feature data of the building to be evaluated into the building energy consumption prediction model to obtain the energy consumption prediction data of the building to be evaluated. The pre-built building energy consumption model is a machine learning model pre-trained using a pre-built building life cycle carbon emission database. The machine learning model includes a linear regression model, a random forest model, a gradient boosting tree model, and a support vector machine model. The linear regression model is suitable for scenarios with simple linear relationships, such as predicting energy consumption based on building area and annual average temperature. The random forest model is suitable for handling multi-dimensional nonlinear characteristics, such as predicting monthly energy consumption by combining building materials, meteorological data, and energy consumption behavior. The gradient boosting tree model is suitable for high-dimensional complex data to provide high-precision predictions, such as predicting annual energy consumption based on the U-value of the exterior wall and hourly meteorological data. Preferably, the gradient boosting tree model uses XGBoost. The support vector machine model is suitable for small and medium-sized datasets and handles complex nonlinear relationships. The pre-built building life cycle carbon emission database contains prototype building model data, future meteorological characteristic data of the prototype building location, energy consumption behavior data of residents in the prototype building location, and a building supply-side dynamic energy model.
[0039] As attached Figure 2 As shown, the process of generating prototype building model data includes the following steps: Step 311: Analyze the design drawings of several existing residential buildings to obtain statistical information on existing buildings; the statistical information on existing buildings includes the basic structural parameters and spatial distribution parameters of existing buildings.
[0040] Step 312: Cluster the existing building statistical information and then use the auxiliary averaging method to obtain the spatial characteristic parameters of typical residential buildings.
[0041] Step 313: Based on the spatial characteristic parameters of typical residential buildings, and in accordance with building design standards, use the Latin hypercube sampling method to combine window-to-wall ratio, number of floors, and thermal performance to obtain several prototype models of residential buildings; among them, the format of several prototype models of residential buildings is IDF data format.
[0042] Example explanation: In this embodiment 1, over 600 sets of existing residential building drawings were collected, and basic information such as building parameters and spatial distribution, including the number of floors, floor height, area, window-to-wall ratio, unit type distribution, and functional zoning, were statistically analyzed. After collecting and statistically analyzing the template building information, K-means clustering was used to identify the number of floors, floor height, area, window-to-wall ratio, unit type distribution, functional zoning, and the area ratio of each functional area to obtain typical prototype building templates. Then, the auxiliary averaging method was used to derive the spatial distribution of typical residential buildings, which served as typical prototype building templates for constructing prototype building models and simulating their energy consumption, serving as input for the database. In accordance with relevant standards, including the thermal design code for civil buildings and the energy-saving design standard for public buildings, Latin hypercube sampling was used to combine window-to-wall ratio, number of floors, and thermal performance to obtain a series of residential building prototype models.
[0043] It should be noted that, in order to generate building models with different window-to-wall ratios, thermal properties of the building envelope, and energy consumption behavior data in batches, the residential building prototype model is first exported as an IDF data file, and then the IDF file is modified. The modification process includes: modifying the window-to-wall ratio (WWR) of the building in the IDF file, and setting target values for the four orientations of North, East, South, and West. The script first loads the IDF file, parses the detailed surface and window objects, and filters out the exterior walls (surface type is wall and the outer boundary is outdoors) and exterior windows (type is window or glass door). Based on the azimuth angle of the exterior walls, the exterior walls and the windows on them are assigned to the four orientation intervals (for example, 315°-45° is North), and the total area of the exterior walls and the total area of the windows for each orientation are calculated. Next, the script calculates the window area scaling factor for each orientation according to the user-defined target window-to-wall ratio, that is, the target window area (exterior wall area multiplied by the target window-to-wall ratio) divided by the current window area, and then taking the square root to obtain the side length scaling ratio. For each window, the script extracts the coordinates of its four vertices, calculates the geometric center, and the current width and height (based on the distance between vertices). Using the azimuth of the exterior wall, the script determines the local coordinate system of the window, adjusts the width and height (multiplied by the side length scaling factor), and recalculates the coordinates of the four vertices around the geometric center to ensure the window remains within the original exterior wall plane. The modified window vertex coordinates are updated in the IDF file, finally saved as a new file, and the adjusted window-to-wall ratio is calculated for verification to ensure it is close to the target value. Precise modification of the window-to-wall ratio is achieved through geometric transformation and area ratio adjustment, suitable for optimizing building lighting and energy consumption simulation. The script also modifies the thermal properties of the building envelope in the IDF file, specifically the thickness and thermal conductivity of a certain material layer, to adjust the building's thermal performance. After loading the IDF file, the script locates the user-specified building envelope (composed of multiple layers of materials) and the target material layer within it. Considering that directly modifying the IDF object may affect the file structure, the script uses text processing, directly reading the raw text of the IDF file and parsing it line by line to find the definition block of the target material (starting with "Material" and matching the material name). Within the material definition block, the script identifies thickness (usually the second field) and thermal conductivity (the third field), replacing them with user-provided new values while preserving indentation, comments, and other content to ensure formatting consistency. The modified text is saved as a new IDF file. The script also counts the number of lines in the original and modified files to verify the reasonableness of the changes (issuing a warning if the difference in line count is too large). Through this text replacement method, the script accurately updates the thermal property parameters of the material, avoiding errors that may be introduced by complex object operations. It is suitable for adjusting the insulation or heat transfer performance of building envelopes to optimize energy consumption simulations, resulting in an IDF file format of the target sample building model.
[0044] It's important to note that the IDF (Input Data File) is the core input file format used by EnergyPlus software to define building simulation models. It's in plain text and has specific structure and syntax rules. Each IDF file consists of a series of objects, each describing a specific attribute or system in the building or simulation, such as building geometry, material properties, HVAC system configuration, schedules, and operating parameters. The object definition begins with the object type, followed by a set of fields, each separated by commas and ending with a semicolon. The top of the file contains a Version object, specifying the corresponding EnergyPlus version. The EnergyPlus IDD (Input Data Dictionary) defines the rules for each object and its fields in the IDF file, such as the number of fields, units, data types, and default values. When using IDF files for building energy consumption simulations, it's necessary to use the corresponding version of the IDD file. Through IDF files, we can flexibly create and modify simulation models, setting the building's thermal performance, equipment operating parameters, and more. IDF files can be edited and manipulated using tools included in EnergyPlus (such as IDF Editor) or third-party libraries (such as Eppy). They can also be modified directly using a text editor. They are a very important file format in building energy consumption simulation. In this embodiment 1, code is written using third-party Python library functions such as Eppy to modify the thermal properties, window-to-wall ratio, and energy consumption behavior data of building digital models with the same geometric appearance. This allows for the rapid and batch generation of building models with different attributes, thereby obtaining a pre-built dynamic carbon emission assessment database for the entire building life cycle.
[0045] As attached Figure 3 As shown, the process of generating future meteorological characteristic data for the location of the prototype building includes the following steps: Step 321: Collect typical meteorological data and actual annual meteorological data of the building location to obtain hourly reference values of meteorological parameters; Step 322: Based on the hourly baseline values of meteorological parameters, generate predicted values with months as the time scale using the HadCM3 climate model and the A2 scenario method. Step 323: Using the Morphing principle, the hourly baseline values of meteorological parameters are fused with the predicted values on a monthly time scale to obtain future meteorological characteristic data for the area where the existing residential buildings are located.
[0046] As attached Figure 4 As shown, the process of generating energy consumption behavior data for the location of the prototype building includes: Step 331: Collect urban population statistics of the building's location, combine them with the spatial characteristic parameters of the prototype building, and use a generative model to generate the population characteristics of the building's residents; the generative model uses a Bayesian network.
[0047] Step 333: Combine the demographic characteristics of building residents with the energy consumption characteristic source data of residents, and use a stochastic model to obtain the energy consumption behavior data of residents; wherein, the energy consumption behavior data of residents includes the use of electrical appliances such as lighting equipment and air conditioning equipment by residents; the energy consumption characteristic source data of residents is the actual energy consumption data of each climate zone investigated according to the national climate zone, that is, the survey data; the stochastic model is a Markov chain model.
[0048] It should be noted that current building occupant demographic characteristics and historical urban population statistics are insufficient. To construct a dynamic carbon emission database, this embodiment 1 utilizes historical statistical data and current population characteristics, combined with a system dynamics model, to extrapolate the building occupant demographic characteristics throughout the building's entire lifecycle. Specifically, it first requires obtaining the current occupant demographic characteristics and then forming a causal loop of system dynamics based on the prototype building's parameters and occupant demographic characteristics, thus obtaining a system dynamics model. Energy consumption behavior in the region is investigated using questionnaires and other methods, and energy consumption behavior data for the target building's occupants throughout their entire lifecycle is generated using a stochastic model.
[0049] In this embodiment 1, the building supply-side dynamic energy model includes a wind power generation model, a photovoltaic power generation model, a hydrogen electrolyzer model, a hydrogen storage tank model, a battery model, a fuel cell model, a combined heat and power model, a solar collector model, an electric chiller model, a gas boiler model, an absorption chiller model, and a thermal storage tank / cold storage tank model.
[0050] (1) Wind power generation model, used to dynamically assess the contribution of wind power generation to building energy supply; by considering the impact of efficiency degradation on long-term power generation, it affects carbon emission accounting; among which, the wind power generation model includes wind power output power model and wind power efficiency degradation model.
[0051] The output power model for wind power generation is as follows:
[0052]
[0053] in, This refers to the output power of the wind turbine. The wind speed at the turbine's height; For cutting speed; Cutting speed; These are parameters that are equal to the rated output power of a wind turbine. The efficiency degradation coefficient for wind power generation; Rated speed; This refers to the rated output power of the wind turbine. Wind speed at reference altitude; This refers to the height of the turbine hub. For reference height; This is the roughness factor.
[0054] The wind power generation efficiency degradation model is as follows:
[0055] in, This represents the efficiency degradation coefficient of the wind turbine. The degradation rate of the wind turbine is taken as 1.6% / year; The usage period is in years.
[0056] (2) Photovoltaic power generation model, used to dynamically assess the contribution of photovoltaic power generation to building energy supply; by considering the impact of efficiency degradation on long-term power generation, it affects carbon emission accounting; among which, the photovoltaic power generation model includes photovoltaic power output power model and photovoltaic power efficiency degradation model.
[0057] The photovoltaic power generation output power model is as follows:
[0058] in, This refers to the power generation capacity of the photovoltaic panel. The area of the photovoltaic panel; Solar irradiance; The power generation efficiency of photovoltaic panels; For inverter efficiency; This represents the efficiency degradation coefficient of photovoltaic power generation. Power generation efficiency under reference conditions; The temperature coefficient of the photovoltaic panel; The parameters are equal to the battery temperature; Temperature under reference conditions; Battery temperature; Ambient temperature; This refers to the standard battery operating temperature. Solar irradiance under reference conditions.
[0059] The photovoltaic power generation efficiency degradation model is as follows:
[0060] in, The degradation rate of the photovoltaic panel; This refers to the usage time of the photovoltaic panels.
[0061] (3) Hydrogen electrolyzer model, used to evaluate the energy storage potential of hydrogen in building energy systems; by considering the impact of efficiency degradation on long-term power generation, it affects carbon emission accounting; among which, the hydrogen electrolyzer model includes output hydrogen quantity model and output hydrogen efficiency degradation model.
[0062] The output hydrogen quantity model is as follows:
[0063] in, To output hydrogen power; For input electrical power; Energy conversion efficiency; The output hydrogen efficiency degradation coefficient; The coefficients are the electrical efficiency function coefficients; Rated input power; The time scale is 1 hour; This is the higher calorific value of hydrogen. This represents the volume of hydrogen gas output. The mass of hydrogen gas output; The value is the molar mass of hydrogen, taken as 0.002 kg / mol; This represents the molar volume of the gas.
[0064] The output hydrogen efficiency degradation model is as follows:
[0065] in, The degradation rate of the hydrogen electrolyzer; This refers to the operating time of the hydrogen electrolyzer.
[0066] (4) Hydrogen storage tank model: dynamically balance hydrogen supply and demand, and optimize the carbon emission contribution of the energy storage system. Hydrogen balance model: The hydrogen storage tank is used to store hydrogen produced by the electrolyzer and supply it to fuel cells or other equipment as needed.
[0067]
[0068] in, This represents the current hydrogen storage capacity. This represents the amount of hydrogen stored at the previous moment. The state of the hydrogen storage tank is 0 when the hydrogen storage tank state is an output and 1 when the hydrogen storage tank state is an input. The amount of hydrogen input at the previous moment; The amount of hydrogen output at the previous moment; This refers to the capacity of the hydrogen storage tank.
[0069] (5) Battery model to evaluate the energy storage efficiency of batteries in building energy systems, taking into account the impact of degradation on carbon emissions.
[0070] State of Electricity (SOC) Model: SOC represents the remaining capacity of a battery and reflects its energy storage state.
[0071] in, The charge level at the current moment; The current battery level; This refers to the battery's rated capacity. The battery level at the previous moment; Self-discharge rate; This represents the battery charging state. The value is 0 when the battery is discharging and 1 when the battery is charging. This refers to the charging power. For charging efficiency; This refers to the discharge power. For discharge efficiency; The time scale is 1 hour; This represents the minimum state of charge. This represents the maximum value of the state of charge. This is the maximum charging power; This represents the maximum discharge power.
[0072] State of Health (SOH) Model: SOH reflects the degree of battery aging, usually expressed as capacity decay.
[0073] in, for The battery health status at any time; This represents the currently available capacity.
[0074] Capacity degradation model: Battery capacity degradation is caused by factors such as cycle count, depth of charge / discharge, and temperature.
[0075] in, for The battery health status at any time; The linear aging coefficient is given.
[0076] (6) Fuel cell model: Evaluate the role of fuel cells in building energy supply, considering the impact of degradation on long-term carbon emissions. Output power model: Fuel cells generate electricity through the chemical reaction of hydrogen and oxygen; the output power depends on the hydrogen input and conversion efficiency.
[0077] in, For output electrical power; For input hydrogen power; For electrical efficiency; This is the efficiency degradation coefficient; These are the efficiency function coefficients; Rated power; Thermoelectric ratio; The coefficient of the thermoelectric ratio function; To output thermal power; The lower heating value of hydrogen; is the molar mass of hydrogen gas; This represents the molar volume of the gas. This is the amount of hydrogen gas to be input.
[0078] Efficiency degradation model: Efficiency degradation is caused by electrode aging, catalyst deactivation, membrane fouling, etc.
[0079] in, The degradation rate of the fuel cell; This refers to the operating time of the fuel cell.
[0080] (7) Combined Heat and Power (CHP) model: Evaluate the overall efficiency of CHP in building energy systems and optimize carbon emissions. Hydrogen output model: CHP systems generate both electricity and heat, typically using natural gas as fuel, with some systems capable of outputting hydrogen (through reforming).
[0081] in, Power input for natural gas; This refers to the amount of natural gas input. The calorific value of natural gas; To output thermal power; For output electrical power; For output electrical power; For electrical efficiency; The coefficients are the electrical efficiency function coefficients; For rated highways; for Thermoelectric ratio at any given time; This is the coefficient of the thermoelectric ratio function.
[0082] Efficiency degradation model: Efficiency degradation is caused by burner aging, heat exchanger fouling, etc.
[0083] in, This is the efficiency degradation coefficient; The degradation rate; This refers to the runtime.
[0084] (8) Solar collector model to assess the contribution of solar thermal collection to building heating and reduce carbon emissions. Hydrogen output model: Solar collectors convert solar radiation into heat energy for heating or hot water supply.
[0085] in, The heat is output to the solar collector; Solar irradiance; For the heat collection area; For heat collection efficiency; This is the efficiency degradation coefficient; The intercept for instantaneous heat collection efficiency; This is the heat loss coefficient; This refers to the inlet water temperature. The ambient temperature at the current moment.
[0086] Efficiency degradation model: Efficiency degradation is caused by factors such as aging of the collector tubes, contamination of the reflector surface, and seal failure.
[0087] in, The degradation rate of the solar collector; This refers to the operating time of the solar collector.
[0088] (9) Electric chiller unit model to assess the impact of the refrigeration system on building energy consumption and carbon emissions. Hydrogen output model: The electric chiller unit provides cooling capacity by driving the refrigeration cycle with electrical energy.
[0089] in, Input power; This is the rated cooling capacity; The rated performance coefficient; This is the capacity function of the temperature curve; This is the energy efficiency ratio function of the temperature curve; This is the energy efficiency ratio function for the PLR curve; This refers to the chiller cycle ratio; The capacity function coefficients of the first temperature curve; The capacity function coefficients of the second temperature curve; This is the temperature for chilled water supply; The capacity function coefficients of the third temperature curve; The capacity function coefficients of the fourth temperature curve; This refers to the inlet temperature of the cooling water. The capacity function coefficients of the fifth temperature curve; The capacity function coefficients of the sixth temperature curve; The energy efficiency ratio function coefficient of the first temperature curve; The energy efficiency ratio function coefficient for the second temperature curve; The energy efficiency ratio function coefficient for the third temperature curve; The energy efficiency ratio function coefficient for the fourth temperature curve; The energy efficiency ratio function coefficient for the fifth temperature curve; The energy efficiency ratio function coefficient of the sixth temperature curve; The coefficients of the energy efficiency ratio function for the first PLR curve; The coefficients of the energy efficiency ratio function for the second PLR curve; Partial load factor; The coefficients of the energy efficiency ratio function for the third PLR curve; Minimum partial load factor; This represents the cooling capacity at the current moment.
[0090] Efficiency degradation model: Efficiency degradation is caused by compressor wear, heat exchanger contamination, etc.
[0091] in, The capacity degradation coefficient of the electric chiller unit; The degradation rate of the electric water chiller unit; This refers to the operating time of the electric chiller unit.
[0092] (10) Gas-fired boiler model: Evaluate the carbon emission contribution of gas-fired boilers and optimize the heating system. Hydrogen output model: Gas-fired boilers generate heat energy by burning natural gas or other fuels.
[0093] in, To output thermal power; Power input for natural gas; For boiler thermal efficiency; This is the efficiency degradation coefficient; This refers to the amount of natural gas input. It is the lower heating value of natural gas; These are the efficiency function coefficients; Rated thermal power.
[0094] Efficiency degradation model: Efficiency degradation is caused by burner aging, heat exchanger fouling, etc.
[0095] in, To reduce the conversion rate of gas-fired boilers; This refers to the operating time of the gas-fired boiler.
[0096] (11) Absorption chiller model to evaluate the role of absorption chillers in building refrigeration. Hydrogen output model: Absorption chillers utilize thermal energy to drive the refrigeration cycle, typically using fuel gas or waste heat as the heat source.
[0097] in, This refers to the cooling capacity; For input thermal power; COP for absorption chillers; This is the capacity degradation coefficient; Efficiency degradation model: Efficiency degradation is caused by absorbent aging, heat exchanger fouling, etc.
[0098] in, The degradation rate; This refers to the runtime.
[0099] (12) Thermal storage tank / cold storage tank model to optimize the energy utilization efficiency of building heating / cooling systems. Heat balance model: Thermal / cold storage tanks are used to store thermal or cold energy to balance supply and demand.
[0100] in, Stored heat / cold at the current moment; This represents the stored heat / cold energy from the previous moment. This is the heat loss coefficient; The value is 1 when the thermal storage state is in thermal storage mode and 0 when the thermal storage state is in heat release mode. For input thermal power; For heat storage efficiency; To output thermal power; For heat release efficiency; The time scale is 1 hour.
[0101] This embodiment 1 focuses on building carbon emission assessment from a life-cycle perspective, thus requiring consideration of the performance changes of the energy supply system and energy storage equipment over time. For the target building, this embodiment 1 fully considers the evolution of energy types, using wind power generation models, photovoltaic power generation models, hydrogen electrolyzer models, hydrogen storage tank models, battery models, fuel cell models, combined heat and power models, solar collector models, electric chiller models, gas boiler models, absorption chiller models, and thermal / cold storage tank models to form a dynamic energy supply model for the building's supply side. For each equipment or system model, input, output, and degradation models are considered to more accurately assess the building's dynamic carbon emissions.
[0102] Step 4: Obtain the dynamic assessment results of building carbon emissions based on the energy consumption forecast data of the building to be assessed. Specifically, determine the carbon emission factor based on the geographical location information and assessment time period information of the building to be assessed; obtain the dynamic assessment results of building carbon emissions based on the energy consumption forecast data and carbon emission factor.
[0103] It should be noted that the dynamic assessment results of building carbon emissions are derived based on the building's geographical location and the assessment period, combined with carbon emission factors under different energy backgrounds. The energy consumed during building operation, such as electricity, natural gas, or fuel oil, typically comes from fossil fuels. Burning these fuels releases greenhouse gases such as carbon dioxide, leading to carbon emissions. Different energy types have different carbon emission intensities, hence their carbon emission factors also differ. For example, the carbon emission factor for coal-fired power generation is much higher than that for renewable energy. This patented method considers the changes in energy type throughout the building's operational lifecycle, making the building carbon emission assessment more accurate. The specific method for obtaining the assessment results from the carbon emission factors is as follows: obtain the carbon emission factor for each energy source, i.e., the carbon dioxide equivalent produced per unit of energy, in units such as kgCO2e / kWh (electricity) or kgCO2e / m³. 3 (Natural gas) These factors vary depending on the region's energy structure and change throughout the building's lifecycle. Then, the energy consumption of each energy source is multiplied by the corresponding emission factor to calculate the emissions of each energy source, and the results are summed to obtain the total carbon emissions.
[0104] For example, a building consumes 10,000 kWh of electricity annually (factor 0.8 kgCO2e / kWh) and 1,000 cubic meters of natural gas. 3 (Factor 2.0 kg CO2e / m 3 The total emissions are 10000×0.8+1000×2.0=10000kgCO2e; for example, in Xi'an in 2025, the main cooling energy source is thermal power generation; while in 2050, the energy type may change to cleaner new energy sources, and the definition of carbon emission factors changes with time and geographical location.
[0105] The dynamic assessment method for building carbon emissions described in Example 1 establishes a building carbon emission assessment database. This database contains prototype building models of various types and regions, and integrates future meteorological characteristics data of the prototype building locations, user energy consumption behavior, and dynamic energy supply models on the supply side, making the dynamic carbon emission assessment of buildings faster and more accurate. By surveying, collecting, and statistically analyzing typical building model templates in different regions, and then using clustering methods, a series of prototype building models are obtained. Energy consumption behavior is integrated into the prototype building models, and the Energy Plus building energy consumption simulation engine is used to simulate the energy consumption of each prototype building model. Finally, a full life-cycle building carbon emission database is obtained, containing a large number of prototype building BIM models distributed in different regions, as well as simulated energy consumption data of these prototype BIM models. By constructing the full life-cycle building carbon emission database, a large amount of building energy consumption data is obtained, including design and demolition data such as material details and spatial parameters, and operational data such as thermal properties, energy consumption behavior, and heating and cooling loads. Using the characteristic data and energy consumption data of a large number of prototype buildings, combined with machine learning technology, a building energy consumption prediction model is obtained. By using the building energy consumption prediction model, users only need to provide the BIM model of the building to be evaluated, then export the building feature data from the BIM model, and apply the feature data to the trained building energy consumption prediction model to obtain its energy consumption, thus avoiding the calculation of complex and high-threshold simulation engines.
[0106] Example 2 As attached Figure 5 As shown in the figure, this embodiment 2 provides a building carbon emission dynamic assessment system, including a model acquisition module, a feature extraction module, an energy consumption prediction module, and a dynamic assessment module.
[0107] The system comprises the following modules: a model acquisition module for acquiring the BIM model of the building to be evaluated; a feature extraction module for extracting features from the BIM model of the building to be evaluated to obtain its building feature data; an energy consumption prediction module for inputting the building feature data of the building to be evaluated into a pre-built building energy consumption prediction model to obtain its energy consumption prediction data; wherein, the pre-built building energy consumption model is a machine learning model pre-trained using a pre-built building lifecycle carbon emission database; the pre-built building lifecycle carbon emission database includes prototype building model data, future meteorological characteristic data of the prototype building's location, energy consumption behavior data of residents in the prototype building's location, and a dynamic energy model of the building supply side; and a dynamic evaluation module for obtaining the dynamic evaluation results of the carbon emissions of the building to be evaluated based on its energy consumption prediction data.
[0108] Example 3 As attached Figure 6As shown, this embodiment 3 provides an electronic device, including: a memory for storing a computer program; a processor for executing the computer program to implement the steps of the dynamic assessment method for building carbon emissions; or, the processor for executing the computer program to implement the functions of each module in the above-mentioned dynamic assessment system for building carbon emissions.
[0109] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a preset function, the instruction segments describing the execution process of the computer program in the electronic device.
[0110] The electronic device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above are examples of electronic devices and do not constitute a limitation on the electronic device. It may include more components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.
[0111] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.
[0112] The memory can be used to store the computer program and / or module. The processor implements various functions of the electronic device by running or executing the computer program and / or module stored in the memory and by calling the data stored in the memory.
[0113] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function (such as sound playback, image playback, etc.). The data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital cards (SD cards), flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.
[0114] Example 4 This embodiment 4 also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned method for dynamic assessment of building carbon emissions.
[0115] If the modules / units integrated in the building carbon emission dynamic assessment system are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
[0116] Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned dynamic assessment method for building carbon emissions, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-mentioned dynamic assessment method for building carbon emissions. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.
[0117] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.
[0118] The building carbon emission dynamic assessment method described in this invention utilizes a machine learning model trained on a building carbon emission database throughout the building's life cycle as a building energy consumption prediction model. It integrates model data from several prototype buildings, future meteorological characteristics data of the prototype building's location, resident energy consumption behavior data, and a building supply-side dynamic energy model into the building carbon emission database throughout the building's life cycle. This fully considers the dynamic changes of different influencing factors in building carbon emission assessment, making the assessment results more consistent with actual changes and more accurately assessing building carbon emissions.
[0119] The above embodiments are merely one of the implementation methods for achieving the technical solution of the present invention. The scope of protection claimed by the present invention is not limited to this embodiment, but also includes any variations, substitutions and other implementation methods that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention.
Claims
1. A method for dynamic assessment of building carbon emissions, characterized in that, include: Obtain the BIM model of the building to be evaluated; Feature extraction is performed on the BIM model of the building to be evaluated to obtain the building feature data of the building to be evaluated; The building characteristic data of the building to be evaluated is input into the pre-built building energy consumption prediction model to obtain the energy consumption prediction data of the building to be evaluated. The pre-built building energy consumption model is a machine learning model pre-trained using a pre-built building life cycle carbon emission database. The pre-built building life cycle carbon emission database includes prototype building model data, future meteorological characteristic data of the prototype building location, energy consumption behavior data of residents in the prototype building location, and building supply-side dynamic energy model. Based on the energy consumption prediction data of the building to be evaluated, the dynamic assessment results of the building's carbon emissions are obtained.
2. The method for dynamic assessment of building carbon emissions according to claim 1, characterized in that, The architectural feature data of the building to be evaluated includes the building's spatial geometric parameters, thermal properties of the building envelope, and material properties; the architectural feature data of the building to be evaluated is saved in the form of a Word document.
3. The method for dynamic assessment of building carbon emissions according to claim 1, characterized in that, The process of generating prototype building model data includes: The design drawings of several existing buildings are analyzed to obtain statistical data on existing buildings; the statistical data on existing buildings includes the basic structural parameters and spatial distribution parameters of existing buildings. Clustering and identification of existing building statistics, and deriving the spatial distribution characteristics of typical prototype buildings through the auxiliary averaging method, thus obtaining a typical prototype building model; Based on predetermined building design standards, the Latin hypercube sampling method is used to generate building models with different window-to-wall ratios, thermal properties of the building envelope, and energy consumption behavior data, thus obtaining prototype building model data.
4. The method for dynamic assessment of building carbon emissions according to claim 3, characterized in that, The process of generating future meteorological characteristic data for the prototype building's location includes: Obtain typical annual meteorological data and actual annual meteorological data for the location of existing buildings; Hourly statistical analysis was conducted on typical annual meteorological data and actual annual meteorological data of the location of the existing building to obtain hourly baseline values of meteorological parameters for the existing building. Based on the hourly reference values of meteorological parameters of existing buildings, meteorological forecast values with a monthly time scale are generated using the HadCM3 climate model and the A2 scenario method. Based on the Morphing principle, the hourly reference values of meteorological parameters of existing buildings are fused with meteorological forecast values on a monthly time scale to obtain future meteorological characteristic data of the prototype building's location.
5. The method for dynamic assessment of building carbon emissions according to claim 3, characterized in that, The process of generating energy consumption behavior data of residents at the prototype building site includes: Based on the demographic data of the location of the existing building and combined with the spatial distribution characteristics of the prototype building, the demographic characteristics of the residents of the existing building are generated. Based on the population characteristics of residents in existing buildings and the energy consumption characteristics of residents in the location of existing buildings, energy consumption behavior data of residents is randomly generated to obtain energy consumption behavior data of residents in the location of the prototype building.
6. The method for dynamic assessment of building carbon emissions according to claim 1, characterized in that, The dynamic energy model for the building supply side includes wind power generation model, photovoltaic power generation model, hydrogen electrolyzer model, hydrogen storage tank model, battery model, fuel cell model, combined heat and power model, solar collector model, electric chiller model, gas boiler model, absorption chiller model, and thermal storage tank / cold storage tank model.
7. The method for dynamic assessment of building carbon emissions according to claim 1, characterized in that, The process of obtaining the dynamic assessment results of carbon emissions of the building to be assessed based on the energy consumption prediction data of the building to be assessed includes: Based on the geographical location information of the building to be evaluated and the evaluation time period information, determine the carbon emission factors corresponding to different energy sources; Based on the carbon emission factors corresponding to different energy sources and the energy consumption prediction data of the building to be evaluated, the dynamic assessment results of the carbon emissions of the building to be evaluated are calculated.
8. A dynamic assessment system for building carbon emissions, characterized in that, include: The model acquisition module is used to acquire the BIM model of the building to be evaluated. The feature extraction module is used to extract features from the BIM model of the building to be evaluated, and obtain the building feature data of the building to be evaluated. The energy consumption prediction module is used to input the building characteristic data of the building to be evaluated into the pre-built building energy consumption prediction model to obtain the energy consumption prediction data of the building to be evaluated; wherein, the pre-built building energy consumption model is a machine learning model pre-trained using a pre-built building carbon emission database throughout the building's life cycle. The pre-built building carbon emission database for the entire building life cycle includes prototype building model data, future meteorological characteristics data of the prototype building location, energy consumption behavior data of residents in the prototype building location, and a dynamic energy model of the building supply side. The dynamic assessment module is used to obtain the dynamic assessment results of the carbon emissions of the building to be assessed based on the energy consumption prediction data of the building.
9. An electronic device, characterized in that, include: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, performs the building carbon emission dynamic assessment method as described in any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the building carbon emission dynamic assessment method as described in any one of claims 1-7.