Building whole life cycle carbon emission calculation method based on multiple linear regression

Abstract

The invention relates to the technical field of carbon emission treatment, in particular to a building full-life-cycle carbon emission calculation method based on multiple linear regression. Comprising the following steps: acquiring carbon emission data of each stage of a building through a BI model, and extracting key characteristic variables such as a material carbon emission coefficient and energy consumption intensity by adopting a Latin hypercube sampling method and a fuzzy clustering algorithm; modeling carbon emission by using a multiple linear regression model, and constructing a carbon emission prediction model; optimizing model parameters through a differential evolution algorithm; and finally, calculating the total amount of carbon emission, analyzing key influence factors in a high-carbon emission stage through a causal reasoning algorithm, proposing an optimization strategy, generating an analysis report, and realizing accurate prediction and effective optimization of the carbon emission in the whole life cycle of the building. According to the method, the carbon emission of the whole life cycle of the building can be accurately evaluated, and powerful support can be provided for optimization decision-making of the carbon emission.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission processing, and in particular to a method for calculating carbon emission over the entire life cycle of a building based on multivariate linear regression. Background Art

[0002] As the global climate change problem becomes increasingly serious, the construction industry, as one of the main sources of carbon emissions, has attracted much attention. The carbon emissions of buildings throughout their life cycle mainly include the stages of material production, construction, use and operation, and final demolition and waste disposal. How to quantify carbon emissions and effectively propose emission reduction strategies throughout the life cycle of buildings has become an important research topic in the field of sustainable development. At present, there are still the following problems: In the existing technology, the acquisition of carbon emission data throughout the life cycle of buildings usually relies on manual or discrete data collection methods, which is prone to incomplete data and low efficiency, and lacks a unified standardized processing process, affecting the accuracy of subsequent analysis; traditional carbon emission calculation methods mostly rely on simple statistical models or single variable analysis, which makes it difficult to fully consider the comprehensive impact of multidimensional factors such as materials, energy, equipment and construction technology, and the prediction results are not accurate enough to meet the actual application needs; traditional methods fail to comprehensively evaluate carbon emissions from the perspective of the entire life cycle of buildings, lack systematic carbon emission management methods, and are difficult to meet the actual needs of low-carbon development of green buildings. Summary of the invention

[0003] To solve the above problems, the present invention provides a method for calculating carbon emissions throughout the life cycle of a building based on multivariate linear regression, which solves the problem of how to comprehensively obtain carbon emission data throughout the life cycle of a building, construct an accurate prediction model for comprehensive analysis of multidimensional factors, and propose an effective low-carbon optimization strategy, thereby accurately evaluating the carbon emissions of a building throughout its life cycle and providing strong support for the optimization decision of carbon emissions.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The method for calculating carbon emissions from the entire life cycle of a building based on multivariate linear regression includes the following steps:

[0006] S1: Obtain carbon emission data at each stage of the building’s life cycle through the BIM model;

[0007] S2: Based on the carbon emission data, Latin hypercube sampling method is used for sampling, and fuzzy clustering algorithm is used for dynamic stratification to extract key characteristic variables of building carbon emissions; the key characteristic variables include material carbon emission coefficient, energy consumption intensity, equipment operation efficiency and construction process carbon emission characteristics;

[0008] S3: Based on the key characteristic variables, a multivariate linear regression model is used to model the carbon emissions of the building throughout its life cycle and to construct a carbon emission prediction model;

[0009] S4: using a differential evolution algorithm to globally optimize the parameters of the carbon emission prediction model, and dynamically adjusting the model parameters through iterative calculation;

[0010] S5: Calculate the total carbon emissions of the building throughout its life cycle, and conduct in-depth analysis of the cause and effect relationship of the high carbon emission stage through causal reasoning algorithms, identify influencing factors, and generate a carbon emission calculation and analysis report through a feedback mechanism.

[0011] Furthermore, the carbon emission data includes design parameters, material types, equipment operation data, energy consumption data and construction process data.

[0012] Furthermore, the step S2 includes the following steps:

[0013] Extract the carbon emission data based on the BIM model, and divide them into material production stage, construction stage, operation and maintenance stage, and demolition stage, and establish data groups respectively;

[0014] Using Latin hypercube sampling method, setting constraints to generate sampling points with uniform distribution characteristics in the data set;

[0015] Combined with the fuzzy clustering algorithm, the carbon emission data is dynamically clustered according to the attribute similarity of the sampling points, forming a multi-layer grouping system based on time, process and equipment type;

[0016] Based on the multi-layer grouping system, a multi-modal fusion feature extraction algorithm is applied to perform analysis and extract key feature variables;

[0017] The identified key feature variables are ranked by weight allocation.

[0018] Furthermore, the formula of the Latin hypercube sampling method is as follows:

[0019]

[0020] Among them, X ij represents the sampling result of the jth variable in the i-th sample, that is, the sampling result of carbon emission data; L j Indicates the minimum value of carbon emission data; H j Indicates the maximum value of carbon emission data; P ij Represents the number of the jth variable in the discrete group after random arrangement; R ij represents a random number that follows a uniform distribution; φ(R ij , σj ) represents the extended disturbance term, which is used to adjust the random number R ij The impact of; n represents the number of sampling points of carbon emission data; k j Represents the periodic disturbance coefficient, which is used to introduce periodic sinusoidal disturbance; Represents a sinusoidal disturbance term, which is used to introduce nonlinear fluctuations in the sampled values ​​of each variable.

[0021] Furthermore, it is characterized in that the construction process of the fuzzy clustering algorithm includes the following steps:

[0022] Generate a fuzzy relationship matrix based on the carbon emission data, and quantify the similarity between the data through a membership function;

[0023] Initialize cluster centers and use a dynamic hierarchical algorithm to assign data points;

[0024] Iteratively optimize the cluster center according to the objective function until the convergence condition is met;

[0025] The clustering results are output to form a multi-layer fuzzy clustering structure of building carbon emission data.

[0026] Furthermore, it is characterized in that the step S3 comprises the following steps:

[0027] Based on the key characteristic variables, a carbon emission prediction model using a multivariate linear regression algorithm is established;

[0028] Using historical carbon emission data, the carbon emission prediction parameters are fitted by the least squares method;

[0029] The stepwise regression method was used to screen and optimize the weights of key characteristic variables;

[0030] The fitting performance and predictive ability of the model are evaluated through cross-validation, and the optimized carbon emission prediction model is finally output.

[0031] Furthermore, it is characterized in that the formula of the carbon emission prediction model is as follows:

[0032]

[0033] Among them, E represents the total carbon emissions over the entire life cycle of the building; β0 represents the basic value of carbon emissions over the entire life cycle of the building; β i represents the linear regression coefficient of the i-th key feature variable; γ j Represents the regression coefficient of the nonlinear term; δ k represents the regression coefficient of the interaction term; n represents the number of key characteristic variables; m represents the total number of square terms; p represents the total number of interaction terms; Indicates the linear contribution of key characteristic variables to total carbon emissions; It represents the contribution of the square term of the key characteristic variable to carbon emissions, which is used to reflect the nonlinear relationship of the variable; It represents the impact of the interaction between two variables on carbon emissions and is used to model the synergistic effect between variables; ∈ represents random errors or changes in carbon emissions that are not explained by the model.

[0034] Furthermore, in step S4, the differential evolution algorithm specifically adopts a dual-objective optimization differential evolution algorithm, takes carbon emission prediction error and computational efficiency as optimization objectives, and dynamically adjusts model parameters.

[0035] Furthermore, in step S5, the causal reasoning algorithm specifically includes a method based on Bayesian networks and structural equation models, which establishes a causal network diagram of carbon emissions throughout the life cycle of a building, utilizes data-driven causal inference technology, identifies and quantifies key influencing factors and their causal paths in the high carbon emission stage, and provides optimization strategy recommendations.

[0036] The beneficial effects of the present invention are:

[0037] The present invention uses the BIM model to automatically obtain carbon emission data at each stage of the building's entire life cycle, improves the efficiency and accuracy of data collection, and lays a solid foundation for subsequent modeling and analysis. The Latin hypercube sampling method is combined with the fuzzy clustering algorithm to dynamically stratify and extract key carbon emission characteristic variables, which can significantly reduce data redundancy, highlight factors that have a greater impact on carbon emissions, and improve the interpretability and analysis efficiency of the model. The multivariate linear regression model is used to model the carbon emissions of the entire life cycle. By considering multidimensional factors such as materials, energy, equipment, and construction technology, a scientific and comprehensive carbon emission prediction model is constructed to provide accurate carbon emission estimation results. The model parameters are globally optimized through the differential evolution algorithm to ensure that the model has higher prediction accuracy and dynamic adaptability, so that it can more flexibly respond to the carbon emission characteristics of different construction projects. The causal reasoning algorithm is used to conduct in-depth analysis of the high carbon emission stage, identify key influencing factors, and provide targeted improvement measures for carbon emission reduction; at the same time, a carbon emission calculation and analysis report is generated through a feedback mechanism to help the building design and construction team optimize the carbon emission management plan. Through comprehensive and accurate carbon emission calculation and analysis, it can provide a scientific basis for carbon management throughout the entire life cycle of buildings, and effectively promote the construction industry to move towards low-carbon and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flow chart of a method for calculating carbon emissions over the entire life cycle of a building based on multivariate linear regression according to the present invention.

[0039] Figure 2 It is a flowchart of step S2 provided in one embodiment of the present invention.

[0040] Figure 3 It is a flowchart of step S3 provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0041] See also Figure 1-3 As shown, the present invention relates to a method for calculating carbon emissions over the entire life cycle of a building based on multivariate linear regression.

[0042] Example

[0043] The method for calculating carbon emissions from the entire life cycle of a building based on multivariate linear regression includes the following steps:

[0044] S1: Obtain carbon emission data at each stage of the building's life cycle through the BIM model; the carbon emission data includes design parameters, material types, equipment operation data, energy consumption data and construction process data.

[0045] Among them, mainstream BIM modeling software (such as Revit, Archicad) is used to create a building model, which contains multi-dimensional information such as building design, structure, equipment, and construction. Import the design parameters of the building (such as building area, height, functional layout, etc.), construction materials (such as reinforced concrete, wood, glass, etc.) and construction technology. Introduce a carbon emission coefficient database (such as the standard coefficient issued by the Ministry of Ecology and Environment, Ecoinvent database, etc.), and associate the carbon emission coefficients of the production, transportation, and construction stages of building materials with the material information in the BIM model. By simulating the energy consumption (such as electricity, gas, renewable energy) and equipment operation data (such as HVAC, lighting systems, elevators, etc.) during the use stage of the building, real data is collected in combination with the energy management system (EMS). According to the full life cycle stage of the building (design, construction, operation, maintenance, and demolition), extract data information related to carbon emissions to form an initial carbon emission data set.

[0046] Divide the building life cycle into the following stages and obtain the corresponding carbon emission data:

[0047] Production stage: involves carbon emissions from the production, transportation and storage of building materials, including the mining, processing and manufacturing of raw materials.

[0048] Construction phase: the use of machinery and equipment, the transportation of construction workers, temporary facilities at the construction site (such as scaffolding), and energy consumption during the construction process.

[0049] Operation phase: energy consumption (electricity, gas, water, etc.) and equipment maintenance and operation during the use of the building.

[0050] Maintenance stage: Carbon emissions involving regular repairs of buildings, replacement of materials and equipment.

[0051] Demolition phase: the dismantling of a building at the end of its life, the transportation and disposal of waste materials (such as recycling or landfill).

[0052] S2: Based on the carbon emission data, Latin hypercube sampling method is used for sampling, and fuzzy clustering algorithm is used for dynamic stratification to extract key characteristic variables of building carbon emissions; the key characteristic variables include material carbon emission coefficient, energy consumption intensity, equipment operation efficiency and construction process carbon emission characteristics;

[0053] Wherein, the step S2 comprises the following steps:

[0054] Extract the carbon emission data based on the BIM model, and divide them into material production stage, construction stage, operation and maintenance stage, and demolition stage, and establish data groups respectively;

[0055] Using Latin hypercube sampling method, setting constraints to generate sampling points with uniform distribution characteristics in the data set;

[0056] It should be noted that in each data set, the variable range is defined (such as the material carbon emission coefficient range is 0.1-2.0 kgCO2 / kg), and constraints are set (such as the upper and lower limits of the total material usage or construction time). Latin hypercube sampling method (through tools such as MATLAB's lhsdesign or Python's pyDOE library) is used to generate sampling points with uniform distribution characteristics to ensure coverage of the variable range.

[0057] The following are examples of constraints:

[0058] Material production stage: constrain the total carbon emissions of each material to not exceed the specified threshold;

[0059] Construction stage: constrain the total energy consumption within a certain range to meet the actual working conditions;

[0060] Operation and maintenance phase: The service life of the building is constrained to 50 years.

[0061] The output sampling points contain multi-dimensional attribute data to ensure representativeness and uniform distribution, such as: material type and its carbon emission coefficient; equipment operation efficiency data; energy consumption data of each process link.

[0062] Combined with the fuzzy clustering algorithm, the carbon emission data is dynamically clustered according to the attribute similarity of the sampling points, forming a multi-layer grouping system based on time, process and equipment type;

[0063] Based on the multi-layer grouping system, a multi-modal fusion feature extraction algorithm is applied to perform analysis and extract key feature variables;

[0064] The identified key feature variables are ranked by weight allocation.

[0065] The construction process of the fuzzy clustering algorithm includes the following steps:

[0066] Generate a fuzzy relationship matrix based on the carbon emission data, and quantify the similarity between the data through a membership function; each value of the matrix represents the degree of similarity between the data points;

[0067] Initialize cluster centers and use a dynamic hierarchical algorithm to assign data points;

[0068] Iteratively optimize the cluster center according to the objective function until the convergence condition is met;

[0069] The clustering results are output to form a multi-layer fuzzy clustering structure of building carbon emission data.

[0070] Furthermore, the formula of the Latin hypercube sampling method is as follows:

[0071]

[0072] Among them, X ij represents the sampling result of the jth variable in the i-th sample, that is, the sampling result of carbon emission data; L j Indicates the minimum value of carbon emission data; H j Indicates the maximum value of carbon emission data; P ij Represents the number of the jth variable in the discrete group after random arrangement; R ij represents a random number that follows a uniform distribution; φ(R ij , σ j ) represents the extended disturbance term, which is used to adjust the random number R ij The impact of; n represents the number of sampling points of carbon emission data; k j Represents the periodic disturbance coefficient, which is used to introduce periodic sinusoidal disturbance; Represents a sinusoidal disturbance term, which is used to introduce nonlinear fluctuations in the sampled values ​​of each variable.

[0073] Specifically, φ(R ij , σ j ) is constructed as follows:

[0074]

[0075] Among them, σ j It represents the volatility factor of the j-th variable and indicates the dynamic characteristics of the variable.

[0076] S3: Based on the key characteristic variables, a multivariate linear regression model is used to model the carbon emissions of the building throughout its life cycle and to construct a carbon emission prediction model;

[0077] Wherein, the step S3 comprises the following steps:

[0078] Based on the key characteristic variables, a carbon emission prediction model using a multivariate linear regression algorithm is established;

[0079] It should be noted that the carbon emission prediction model uses the total carbon emissions over the entire life cycle as the dependent variable and key characteristic variables (such as material carbon emission coefficient, energy consumption intensity, equipment operation efficiency and construction process carbon emission characteristics) as independent variables. The model assumes that the impact of each characteristic variable on the total carbon emissions is a linear relationship.

[0080] The extracted key characteristic variables and the corresponding historical carbon emission data are sorted out to form the data set required for modeling. The data set includes: Input variables: such as material carbon emission coefficient, energy consumption intensity, etc. Output variables: total carbon emissions over the entire life cycle. Standardize the data and convert data of different dimensions into dimensionless values ​​to ensure that the characteristic variables are on the same scale. Construct an initial multiple linear regression model and express the contribution of each key characteristic variable as a model parameter.

[0081] Using historical carbon emission data, the carbon emission prediction parameters are fitted by the least squares method;

[0082] Specifically, obtain carbon emission data sets from historical data or actual measurements in the construction industry (such as full life cycle carbon emission records of multiple projects). The data samples need to cover a wide range of building types, scales, and life cycle characteristics to improve the universality of the model. Using the least squares method, adjust the regression coefficients to minimize the sum of squared errors between the predicted values ​​and the actual values. Through iterative optimization, the model can match the historical data to the greatest extent. Output the initial regression coefficient of each characteristic variable as its impact weight on the total carbon emissions. Provide preliminary error assessment results (such as mean square error) to judge the preliminary effect of fitting.

[0083] The stepwise regression method was used to screen and optimize the weights of key characteristic variables;

[0084] The fitting performance and predictive ability of the model are evaluated through cross-validation, and the optimized carbon emission prediction model is finally output.

[0085] Furthermore, the formula of the carbon emission prediction model is as follows:

[0086]

[0087] Where E represents the total carbon emissions over the entire life cycle of the building; β0 represents the basic value of carbon emissions over the entire life cycle of the building, that is, the predicted value when all variables are zero; β i represents the linear regression coefficient of the i-th key characteristic variable, and the impact of each unit increase in the variable on carbon emissions; γ j Represents the regression coefficient of the nonlinear term; δ k represents the regression coefficient of the interaction term; n represents the number of key characteristic variables; m represents the total number of square terms; p represents the total number of interaction terms; Indicates the linear contribution of key characteristic variables to total carbon emissions; It represents the contribution of the square term of the key characteristic variable to carbon emissions, which is used to reflect the nonlinear relationship of the variable; It represents the impact of the interaction between two variables on carbon emissions and is used to model the synergistic effect between variables; ∈ represents random errors or changes in carbon emissions that are not explained by the model.

[0088] S4: Using a differential evolution algorithm to globally optimize the parameters of the carbon emission prediction model, and dynamically adjust the model parameters through iterative calculation; the differential evolution algorithm specifically uses a dual-objective optimization differential evolution algorithm, takes carbon emission prediction error and computational efficiency as optimization objectives, and dynamically adjusts the model parameters.

[0089] Specifically, a set of different model parameter combinations are randomly generated. These combinations can be regarded as a group of candidate solutions. Each set of parameters includes key variables such as the initial regression coefficient and intercept of the model. Each parameter combination represents a possible model solution. By setting the population size (e.g., 50 sets of parameters), the algorithm is ensured to have sufficient diversity. The parameter range is set according to the actual carbon emission data. For example, the weight range of the material carbon emission coefficient is from low to high, and the value of the initial parameter is evenly distributed.

[0090] Each candidate parameter combination is run through the model to calculate the model's error in predicting carbon emissions, as well as the efficiency of the model's operation (such as computing time). Here, a known data sample (such as a validation set) is used for evaluation to determine whether each set of parameters is reasonable. For example: if the prediction error is small and the computing time is short, it means that this set of parameters is better than other combinations. If a set of parameters causes an error that is too large or the running time is too long, this combination may be eliminated.

[0091] Based on the results of the previous round of evaluation, a new parameter combination is generated. This step is called "mutation", which means making slight adjustments to the existing parameters to explore a better solution.

[0092] The range of parameter adjustment is dynamic, allowing a larger exploration range in the early stage. As the optimization iterations proceed, the range is gradually narrowed to find more precise parameters.

[0093] Based on the mutated parameters, a new candidate solution is generated through the "crossover" step by combining the advantages of different combinations. For example, one combination has a better material carbon emission weight, while another combination has a better energy consumption weight. The system will try to integrate these advantages. The crossover parameter combination is evaluated again by the model, and the winner enters the next round of optimization, while the inferior combination is eliminated.

[0094] After each round of iteration, the algorithm generates better parameter combinations, continuously reducing prediction errors and improving computational efficiency.

[0095] The optimization process stops when: the prediction error reaches the preset minimum standard, such as a relative error of less than 1%; the parameter change amplitude approaches zero, indicating that the algorithm has found the optimal solution; the maximum number of iterations is reached to ensure that the algorithm does not run indefinitely.

[0096] After the optimization is completed, the algorithm outputs the final optimal parameters, which will be used for the full life cycle prediction of building carbon emissions. The output includes the weight allocation of each key characteristic variable (such as the influence weight of material carbon emission coefficient is 30%, the influence weight of energy consumption is 50%) and the overall performance indicators of the model (such as prediction error, calculation efficiency, etc.).

[0097] S5: Calculate the total carbon emissions of the building over its entire life cycle, and conduct an in-depth analysis of the causal relationship in the high carbon emission stage through a causal reasoning algorithm, identify the influencing factors, and generate a carbon emission calculation and analysis report through a feedback mechanism; the causal reasoning algorithm specifically includes a method based on a Bayesian network and a structural equation model, which establishes a causal network diagram of carbon emissions over the entire life cycle of the building, uses data-driven causal inference technology, identifies and quantifies the key influencing factors and their causal paths in the high carbon emission stage, and provides optimization strategy recommendations.

[0098] In one embodiment, a Bayesian network is used to represent different stages of the building life cycle and their key characteristic variables as nodes. The relationship between nodes (causal path) is defined, for example:

[0099] Material type → Material carbon emission coefficient → Carbon emissions in the production stage.

[0100] Equipment efficiency → energy consumption → carbon emissions during operation.

[0101] Construction technology → equipment usage time → carbon emissions during the construction phase.

[0102] Through statistical analysis of carbon emission data, direct and indirect relationships between variables can be inferred. For example, carbon emissions during the operation of high-energy-consuming buildings are significantly affected by the thermal properties of materials.

[0103] The structural equation model (SEM) is used to analyze the strength of the causal path and quantify the contribution of each variable to carbon emissions. For example, it is found that the material carbon emission coefficient contributes 70% to carbon emissions in the production stage. Combined with the results of causal network analysis, the main influencing factors in the high carbon emission stage are identified. For example:

[0104] Operation phase: Energy consumption intensity is the main influencing factor.

[0105] Construction phase: The long-term use of tower crane equipment is the key reason for high carbon emissions.

[0106] For each key factor, quantify the impact, for example, a 10% increase in equipment efficiency can reduce carbon emissions during the operation phase by 5%.

[0107] Based on the results of causal analysis, an optimization strategy is proposed. For example:

[0108] Prefer low-carbon emission materials: Replace traditional high-carbon materials (such as ordinary cement) with green building materials (such as low-clinker cement).

[0109] Improve equipment operating efficiency: Upgrade HVAC systems or adopt more efficient renewable energy.

[0110] Optimize construction technology: reduce the operating time of tower cranes and concrete mixers, and adopt low-carbon construction methods.

[0111] Quantify the potential carbon reduction effect of each optimization strategy. For example, using LED lighting instead of traditional lamps can reduce carbon emissions in the operation phase by 15%.

[0112] Feedback loop mechanism: The optimized strategy is reloaded and simulated through the BIM model to verify the actual carbon reduction effect of the optimization scheme. If the optimization effect does not meet the target, the model parameters or strategy scheme can be adjusted again until the result meets the expectation.

[0113] In summary, the present invention comprehensively extracts carbon emission data for the entire life cycle of a building through the combination of a BIM model and a carbon emission coefficient database, covering the production, construction, operation, maintenance and demolition stages, making carbon emission calculations more comprehensive and accurate. The use of Latin hypercube sampling and fuzzy clustering algorithms makes data processing efficient and representative, greatly improving the accuracy of the prediction model. The differential evolution algorithm is used to globally optimize the parameters of the carbon emission prediction model, and the model parameters can be dynamically adjusted to reduce prediction errors and improve computational efficiency. Through iterative optimization, the optimal parameters of the carbon emission prediction model for the entire life cycle are output, making the prediction model more adaptable and universal.

[0114] The present invention introduces the causal reasoning algorithm of Bayesian network and structural equation model to identify the key influencing factors and causal paths of the high carbon emission stage of the whole life cycle of the building. Through causal analysis, the contribution rate of each variable to carbon emissions can be quantified, providing a scientific basis for carbon emission reduction strategies. A carbon emission optimization feedback mechanism is established, and an operational emission reduction optimization strategy (such as selecting low-carbon materials, optimizing construction processes, improving equipment efficiency, etc.) is proposed based on the results of causal analysis. The optimized strategy is verified by the BIM model to achieve a closed loop from data extraction, prediction, optimization to feedback, thereby improving the effectiveness and reliability of the carbon emission reduction plan.

[0115] The present invention is based on multiple linear regression, combined with nonlinear terms and interaction terms for modeling, and is applicable to construction projects of different types and sizes, with strong universality. By extracting data in stages and performing dynamic hierarchical analysis, it can flexibly respond to the carbon emission calculation needs of different building life cycle characteristics. By accurately identifying and quantifying key influencing factors, a quantitative emission reduction effect evaluation is provided. For example, improving equipment efficiency, selecting green building materials, or optimizing construction processes can significantly reduce carbon emissions throughout the life cycle of a building, providing strong support for green building design and construction.

[0116] The above implementation modes are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary engineering and technical personnel in the field shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for calculating carbon emissions over the entire life cycle of a building based on multivariate linear regression, characterized in that: The following steps are involved: S1: Obtain carbon emission data at each stage of the building’s life cycle through the BIM model; S2: Based on the carbon emission data, Latin hypercube sampling method is used for sampling, and fuzzy clustering algorithm is used for dynamic stratification to extract key characteristic variables of building carbon emissions; the key characteristic variables include material carbon emission coefficient, energy consumption intensity, equipment operation efficiency and construction process carbon emission characteristics; S3: Based on the key characteristic variables, a multivariate linear regression model is used to model the carbon emissions of the building throughout its life cycle and to construct a carbon emission prediction model; S4: using a differential evolution algorithm to globally optimize the parameters of the carbon emission prediction model, and dynamically adjusting the model parameters through iterative calculation; S5: Calculate the total carbon emissions of the building throughout its life cycle, and conduct in-depth analysis of the cause and effect relationship of the high carbon emission stage through causal reasoning algorithms, identify influencing factors, and generate a carbon emission calculation and analysis report through a feedback mechanism.

2. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 1 is characterized in that: The carbon emission data includes design parameters, material types, equipment operation data, energy consumption data and construction process data.

3. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 1 is characterized in that: The step S2 comprises the following steps: Extract the carbon emission data based on the BIM model, and divide them into material production stage, construction stage, operation and maintenance stage, and demolition stage, and establish data groups respectively; Using Latin hypercube sampling method, setting constraints to generate sampling points with uniform distribution characteristics in the data set; Combined with the fuzzy clustering algorithm, the carbon emission data is dynamically clustered according to the attribute similarity of the sampling points, forming a multi-layer grouping system based on time, process and equipment type; Based on the multi-layer grouping system, a multi-modal fusion feature extraction algorithm is applied to perform analysis and extract key feature variables; The identified key feature variables are ranked by weight allocation.

4. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 3 is characterized in that: The formula of the Latin hypercube sampling method is as follows: Among them, X ij represents the sampling result of the jth variable in the ith sample, that is, the sampling result of carbon emission data; L j Indicates the minimum value of carbon emission data; H j Indicates the maximum value of carbon emission data; P ij Represents the number of the jth variable in the discrete group after random arrangement; R ij represents a random number that follows a uniform distribution; φ(R ij , σ j ) represents the extended disturbance term, which is used to adjust the random number R ij The influence of; n represents the number of sampling points of carbon emission data; κ j Represents the periodic disturbance coefficient, which is used to introduce periodic sinusoidal disturbance; Represents a sinusoidal disturbance term, which is used to introduce nonlinear fluctuations in the sampled values ​​of each variable.

5. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 3 is characterized in that: The construction process of the fuzzy clustering algorithm includes the following steps: Generate a fuzzy relationship matrix based on the carbon emission data, and quantify the similarity between the data through a membership function; Initialize cluster centers and use a dynamic hierarchical algorithm to assign data points; Iteratively optimize the cluster center according to the objective function until the convergence condition is met; The clustering results are output to form a multi-layer fuzzy clustering structure of building carbon emission data.

6. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 1 is characterized in that: The step S3 comprises the following steps: Based on the key characteristic variables, a carbon emission prediction model using a multivariate linear regression algorithm is established; Using historical carbon emission data, the carbon emission prediction parameters are fitted by the least squares method; The stepwise regression method was used to screen key characteristic variables and optimize their weights; The fitting performance and predictive ability of the model are evaluated through cross-validation, and the optimized carbon emission prediction model is finally output.

7. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 6 is characterized in that: The formula of the carbon emission prediction model is as follows: Among them, E represents the total carbon emissions over the entire life cycle of the building; β0 represents the basic value of carbon emissions over the entire life cycle of the building; β i represents the linear regression coefficient of the i-th key feature variable; γ j Represents the regression coefficient of the nonlinear term; δ k represents the regression coefficient of the interaction term; n represents the number of key characteristic variables; m represents the total number of square terms; p represents the total number of interaction terms; Indicates the linear contribution of key characteristic variables to total carbon emissions; It represents the contribution of the square term of the key characteristic variable to carbon emissions, which is used to reflect the nonlinear relationship of the variable; It represents the impact of the interaction between two variables on carbon emissions and is used to model the synergistic effect between variables; ∈ represents random errors or changes in carbon emissions that are not explained by the model.

8. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 1 is characterized in that: In step S4, the differential evolution algorithm specifically adopts a dual-objective optimization differential evolution algorithm, takes carbon emission prediction error and computational efficiency as optimization objectives, and dynamically adjusts model parameters.

9. The method for calculating carbon emissions from a building throughout its life cycle based on multiple linear regression according to claim 1 is characterized in that: In step S5, the causal reasoning algorithm specifically includes a method based on Bayesian networks and structural equation models. By establishing a causal network diagram of carbon emissions throughout the life cycle of a building, data-driven causal inference technology is used to identify and quantify key influencing factors and their causal paths in the high carbon emission stage, and provide optimization strategy recommendations.

Images