Highway full life cycle carbon emission statistical accounting method

Abstract

The invention discloses a highway full life cycle carbon emission statistical accounting method, and relates to the technical field of carbon emission accounting, and the method comprises the steps: dividing the highway full life cycle into a plurality of stages, and dynamically calibrating the accounting boundary of each stage based on the space-time dimension; setting all types of carbon emission accounting indexes, and collecting multi-modal data corresponding to each stage; establishing a hierarchical computing architecture based on an edge-cloud collaborative technology, checking the carbon emission of each stage, and verifying a carbon emission checking result by using a virtual road model capable of online learning and updating; and drawing a carbon footprint thermodynamic diagram based on a carbon emission accounting result, and displaying a space-time evolution process. According to the invention, the construction, operation and demolition stages of the whole life cycle of the expressway are covered, and the comprehensiveness and systematicness of an accounting result are ensured; a plurality of data sources and collection methods are adopted, and a corresponding accounting method is combined for calculation, so that the accuracy and reliability of an accounting result are ensured, and a scientific basis is provided for low-carbon construction and operation of the expressway.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission accounting, and particularly to a method for statistical accounting of carbon emissions in the whole life cycle of expressways. Background Art

[0002] With the increasingly severe problem of global climate change, reducing greenhouse gas emissions has become the common responsibility of the international community. As an important transportation infrastructure, the carbon emissions generated during the whole life cycle (construction, operation, demolition) of expressways cannot be ignored.

[0003] At present, there are various methods for carbon emission accounting at home and abroad, such as the emission factor method, mass balance method, and actual measurement method, etc. These methods have been widely used in different fields and emission source types. However, for the specific field of expressways, a complete and systematic method for statistical accounting of carbon emissions in the whole life cycle has not been formed. Existing methods mostly focus on carbon emission accounting in a single stage, ignoring the carbon emission characteristics and interrelationships in different stages of the whole life cycle of expressways, resulting in inaccurate and incomplete accounting results.

[0004] The existing methods for carbon emission accounting of expressways mainly have the following deficiencies: 1. The accounting boundary is not clear: Existing methods often only focus on carbon emissions in a certain stage of expressways, ignoring the statistical accounting of carbon emissions in the whole life cycle. 2. The data source is single: Mostly relying on theoretical calculations or limited actual monitoring data, lacking comprehensive and systematic data support. 3. The accounting methods are not unified: There are significant differences between different methods, and the accounting results lack comparability and accuracy. Summary of the Invention

[0005] Based on this, it is necessary to provide a method for statistical accounting of carbon emissions in the whole life cycle of expressways for the above technical problems.

[0006] In the first aspect, the present invention provides a method for statistical accounting of carbon emissions in the whole life cycle of expressways, including:

[0007] S1. Divide the whole life cycle of expressways into multiple stages, and dynamically calibrate the accounting boundary of each stage based on the spatio-temporal dimension;

[0008] S2. Set carbon emission accounting indicators of all types, and collect multi-modal data corresponding to each stage;

[0009] S3. Build a hierarchical computing architecture based on edge-cloud collaborative technology, calculate the carbon emissions of each stage, and use a virtual highway model that can be updated by online learning to verify the carbon emission accounting results;

[0010] S4. Draw a carbon footprint heat map based on the carbon emission accounting results to display the spatio-temporal evolution process.

[0011] Further, divide the whole life cycle of expressways into multiple stages, and based on the spatio-temporal dimension, dynamically calibrate the accounting boundaries of each stage, including:

[0012] S11. Divide the whole life cycle of expressways into construction stage, operation stage and demolition stage, and dynamically adjust the duration of each stage according to the actual progress of the project;

[0013] S12. Use the engineering information of expressways combined with geographic information system and building information model to define the physical impact scope and emission responsibility area of carbon emissions in each stage;

[0014] S13. Construct a carbon flow transfer matrix between each stage to quantify the transfer effect of carbon emissions in each stage.

[0015] Further, dynamically adjusting the duration of each stage according to the actual progress of the project includes:

[0016] S111. Obtain the building information model and construction machinery data of expressway projects, divide the expressway construction area into several cell grids, and generate a machinery coverage matrix;

[0017] S112. Compare the actual coverage grid of the expressway with the designed grid, calculate the real-time progress, and use the long short-term memory network to predict the future construction progress. When the construction progress is greater than the preset progress threshold, switch the expressway from the construction stage to the operation stage, and mark the construction and operation time information;

[0018] S113. Obtain the pavement performance index of the expressway. When the pavement performance index is lower than the preset performance threshold, switch the expressway from the operation stage to the demolition stage, and mark the demolition time information.

[0019] Further, build a hierarchical computing architecture based on edge-cloud collaborative technology to calculate the carbon emissions of each stage, and use a virtual highway model that can be updated online through learning to verify the carbon emission calculation results, including:

[0020] S31. Build a hierarchical computing architecture composed of an edge layer, a fog layer and a cloud layer, and deploy them on the construction machinery side, section management center and traffic control platform in sequence to achieve the whole life cycle calculation of expressways; S32. Use the hierarchical computing architecture to calculate the total construction carbon emissions in the construction stage;

[0021] S33. Use the hierarchical computing architecture to calculate the total operation carbon emissions at the road network level during the operation stage;

[0022] S34. Use the hierarchical computing architecture to calculate the total demolition carbon emissions during the demolition stage, and conduct an overall life cycle integration;

[0023] S35. Construct a virtual highway model based on digital twins, introduce an incremental online learning mechanism, integrate the computing data of each layer within the hierarchical computing architecture, and achieve cross-stage and cross-time-space coupled simulation.

[0024] Furthermore, calculating the total construction carbon emissions during the construction stage using the hierarchical computing architecture includes:

[0025] S321. Divide the multi-modal data during the construction stage into different construction emission types, extract the corresponding accounting indicators, and the construction emission types include equipment operation, building material production, and transportation;

[0026] S322. Use the edge layer to calculate the single-machine carbon emissions of each construction emission type during the construction stage;

[0027] S323. Use the fog layer to unify the mechanical trajectories of construction machinery and the coordinates of the building information model during the construction stage, calibrate the clocks of various devices, and integrate and calculate the total construction carbon emissions during the construction stage;

[0028] S324. Use the cloud layer to match the factor libraries of construction machinery and building materials, dynamically update the edge layer and the fog layer, and real-time monitor the abnormal accounting data existing in the edge layer and the fog layer.

[0029] Furthermore, calculating the total operation carbon emissions at the road network level during the operation stage using the hierarchical computing architecture includes:

[0030] S331. Divide the multi-modal data during the operation stage into different operation emission types, extract the corresponding accounting indicators, and the operation emission types include transportation means and facility maintenance;

[0031] S332. Use the edge layer to preprocess the multi-modal data and extract the non-stop toll collection data, mobile phone signaling data, and road surface monitoring data of transportation means in each accounting indicator;

[0032] S333. Use the fog layer to integrate the electronic non-stop toll collection data and mobile phone signaling data, generate a minute-level traffic flow matrix, calculate the traffic flow carbon emissions, and combine with the calculated road surface maintenance carbon emissions to generate the total operation carbon emissions of a single expressway during the operation stage;

[0033] S334. Use the cloud layer to conduct microscopic traffic simulation, simulate the correlation curve between the congestion index and emissions, and calculate the carbon emissions of the entire road network through road network-level integrated parallel computing.

[0034] Furthermore, calculating the total demolition carbon emissions during the demolition stage using the hierarchical computing architecture and conducting full-life cycle integration includes:

[0035] S341. Divide the multi-modal data in the demolition stage into different demolition emission types, extract the corresponding accounting indicators, and the demolition emission types include demolition equipment types and waste treatment types;

[0036] S342. Use the edge layer to identify and record the waste data existing on the highway and the usage data of demolition equipment;

[0037] S343. Use the fog layer to generate a unique digital ID for each batch of recycled waste, record the transportation distance, treatment process and reuse project of the waste, and calculate the total demolition carbon emissions during the demolition stage;

[0038] S344. Use the cloud layer to perform circular economy offset calculations, integrate and calculate the carbon emission distribution and total carbon emissions of the entire life cycle of the highway, store the output results of each layer in the cloud, and record the source, processing path and quality label of each piece of data through data lineage tracking.

[0039] Furthermore, construct a digital twin-based virtual highway model, introduce an incremental online learning mechanism, integrate the calculation data of each layer in the hierarchical calculation architecture, and realize cross-stage, cross-time and space coupling simulation, including:

[0040] S351. Combine geographic information systems, building information models and multi-physics field coupling to construct a digital twin-based virtual highway model, and integrate the output data of the hierarchical calculation architecture;

[0041] S352. Embed an incremental online learning module in the virtual highway model, regularly update the edge and cloud data, and adjust and correct the model parameters in the virtual highway model;

[0042] S353. Use the virtual highway model to perform coupling simulation among different stages, regions and time periods during the entire life cycle of the highway, and simulate the mutual relationship of different stages;

[0043] S354. Generalize and adapt the virtual highway model by constructing a highway knowledge graph.

[0044] Furthermore, use the virtual highway model to perform coupling simulation among different stages, regions and time periods during the entire life cycle of the highway, and simulate the mutual relationship of different stages, including:

[0045] S3531. Establish state vectors for the construction stage, operation stage and demolition stage respectively;

[0046] S3532. Introduce a multi-scale simulation module in the virtual highway model, use the spatio-temporal coupling simulation algorithm, and interactively integrate the multi-modal data and calculation results of each stage and region;

[0047] S3533. In the multi-scale simulation module at each stage, data is transmitted through a unified interface. Adopting a hierarchical simulation strategy, the local short-term dynamics and the global long-term trends are integrated to achieve cross-time and space simulation; S3534. Taking the carbon emission data output by the hierarchical computing architecture as the true accounting value, it is compared with the carbon emission prediction value of the coupled simulation of the virtual highway model to quantitatively evaluate the difference between the prediction value and the true accounting value, and the difference value is fed back to the incremental online learning module to optimize the parameters of the virtual highway model.

[0048] Furthermore, by constructing a highway knowledge graph, the generalization adaptation of the virtual highway model includes:

[0049] S3541. Set a unified feature space, use the pre-trained model as a feature extractor, freeze the underlying network of the virtual highway model, and build a transfer learning framework;

[0050] S3542. Construct a highway knowledge graph to store highway prior knowledge, and when a new project is input, automatically match similar historical cases to initialize the model parameters of the virtual highway model.

[0051] The beneficial effects of the present invention are as follows:

[0052] 1. The present invention covers the construction, operation, and demolition stages in the whole life cycle of the highway, ensuring the comprehensiveness and systematicness of the accounting results; adopting multiple data sources and collection methods, combined with corresponding accounting methods for calculation, ensuring the accuracy and reliability of the accounting results; at the same time, providing detailed accounting processes and steps, which are convenient for actual operation and application, and providing a scientific basis for the low-carbon construction and operation of the highway.

[0053] 2. By dividing the whole life cycle of the highway into construction, operation, and demolition stages, dynamically calibrating the accounting boundaries at each stage based on the time and space dimensions, the refined management of carbon emissions throughout the process and all time periods is realized; adopting the dynamic boundary correction technology can accurately capture the project progress and environmental changes, ensuring the timeliness and representativeness of the carbon emission data at each stage, thus breaking through the limitations of the traditional method with a single stage division and incomplete data collection, providing a scientific basis for green construction and low-carbon operation, not only significantly improving the accuracy and credibility of the accounting results, but also providing data support for the subsequent optimization of carbon emission reduction strategies and environmental impact assessment.

[0054] 3. By setting carbon emission indicators for all types and collecting multi-modal data corresponding to each stage, the efficient integration of various types of information is achieved. With the help of the edge-cloud collaborative hierarchical computing architecture, on-site sensing and historical data can be processed in real time, and the data fusion algorithm is used to eliminate the differences brought by a single accounting method. At the same time, the virtual highway model updated by online learning dynamically verifies and self-corrects the calculation results, ensuring that the accounting results at each stage reach a high level in terms of accuracy and comparability, thereby effectively reducing data noise and errors and improving the scientificity and adaptability of the full-life-cycle carbon emission accounting. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0056] Figure 1 is a flowchart of a method for statistical accounting of carbon emissions in the full life cycle of a highway according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] Please refer to Figure 1 , which provides a method for statistical accounting of carbon emissions in the full life cycle of a highway, including:

[0059] S1. Divide the full life cycle of the highway into multiple stages, and dynamically calibrate the accounting boundary of each stage based on the space-time dimension.

[0060] In the description of the present invention, dividing the full life cycle of the highway into multiple stages and dynamically calibrating the accounting boundary of each stage based on the space-time dimension includes:

[0061] S11. Divide the full life cycle of the highway into a construction stage, an operation stage, and a demolition stage, and dynamically adjust the duration of each stage according to the actual progress of the project.

[0062] Specifically, the present invention divides the full life cycle of the highway into a construction stage, an operation stage, and a demolition stage, and respectively determines the accounting boundary of each stage, including the following aspects:

[0063] 1. Construction stage: including processes such as design, construction, and installation, and the accounting boundary covers aspects such as the operation of construction equipment, the production and transportation of building materials, etc.

[0064] 2. Operation stage: including aspects such as daily maintenance, servicing, and use. The accounting boundary covers aspects such as the operation of transportation vehicles, and the maintenance and servicing of facilities.

[0065] 3. Demolition stage: including aspects such as the demolition of facilities and waste treatment. The accounting boundary covers aspects such as demolition equipment and waste treatment.

[0066] In the description of the present invention, dynamically adjusting the duration of each stage according to the actual progress of the project includes:

[0067] S111. Obtain the building information model and construction machinery data of the highway project, divide the highway construction area into several cell grids, and generate a machinery coverage matrix.

[0068] Specifically, use the BIM system (Building Information Model) to extract the detailed spatial information of the construction area, including road alignment, component location, and material layout. At the same time, real-time collect the location information and working status data from the sensors of construction machinery (such as excavators, bulldozers, cranes, etc.). According to the actual size and construction characteristics of the construction area, divide the entire construction area into several uniform cell grids. Each grid represents a minimum construction unit, facilitating subsequent monitoring and progress analysis.

[0069] Statistically analyze the coverage of each grid by each piece of machinery in different time periods to form a machinery coverage matrix. Each element in the matrix represents the machinery operation situation of the corresponding grid at a specific time, providing a quantitative basis for real-time assessment of the construction progress.

[0070] S112. Compare the actual coverage grid of the highway with the designed grid, calculate the real-time progress, and use a long short-term memory network to predict the future construction progress. When the construction progress is greater than the preset progress threshold, switch the highway from the construction stage to the operation stage, and mark the construction and operation time information.

[0071] Specifically, by comparing the actual construction coverage grid with the designed grid layout, calculate the current construction progress, and at the same time use a long short-term memory network (LSTM) to predict the future construction progress. The specific implementation process is as follows:

[0072] 1. Progress comparison and analysis: Compare the actual machinery coverage matrix obtained in S111 with the pre-designed ideal coverage matrix, and statistically analyze the ratio of the number of actually covered cells to the total number of designed coverage cells, so as to obtain the real-time construction progress index.

[0073] 2. Progress prediction: Use the LSTM model to train the historical progress data to capture the long-term dependence and trend of progress changes. The input of the model is the coverage rate data within a continuous time period, and the output is the predicted value of the construction progress within a future period of time.

[0074] 3. Phase Switching Judgment: When the real-time or predicted construction progress exceeds the preset progress threshold, the system automatically determines that the project has basically completed the construction phase. At this time, a phase switch is triggered, and the current state is switched from the "construction phase" to the "operation phase". Meanwhile, the time information at the end of the construction phase and the start of the operation phase is recorded to ensure accurate marking of time data.

[0075] S113. Obtain the pavement performance index of the expressway. When the pavement performance index is lower than the preset performance threshold, switch the expressway from the operation phase to the demolition phase and mark the demolition time information.

[0076] Specifically, by obtaining the pavement performance index, monitor the operation status of the expressway and determine whether to enter the demolition phase. The specific implementation process is as follows:

[0077] 1. Performance Index Collection: Use on-site detection equipment or remote sensing monitoring systems to collect the performance indicators of the expressway pavement in real time, such as flatness, crack rate, wear degree, etc. Through data processing, a unified pavement performance index is formed.

[0078] 2. Performance Threshold Comparison: Compare the current pavement performance index with the preset performance threshold. When the index is lower than the threshold, it indicates that the pavement has suffered significant damage or potential safety hazards.

[0079] 3. Phase Switching and Time Marking: When it is detected that the pavement performance index is lower than the preset value, the system automatically determines the end of the operation phase and triggers the conversion from the operation phase to the demolition phase. Meanwhile, record the start time of the demolition phase to provide a time identifier for subsequent demolition operations and carbon emission accounting.

[0080] S12. Utilize the expressway project information in combination with the geographic information system and building information model to define the physical impact scope and emission responsibility areas of carbon emissions in each phase.

[0081] Specifically, collect the detailed design data, construction records, and operation management information of the expressway project through the project management system, including road alignment, structural composition, material list, construction technology, and operation and maintenance plan, etc. Meanwhile, extract the three-dimensional building information model from the BIM system to obtain engineering components, equipment layout, and material usage; use the GIS platform to collect the geospatial data of the project area, such as terrain, land use, ecological environment, transportation network, and administrative divisions, etc. Align these multi-source data in space and time to form a unified data basis.

[0082] Seamlessly connect the BIM model with the GIS (Geographic Information System) platform to achieve complementary information through spatial overlay analysis. For example, by integrating the component locations in BIM with data such as geographical locations, environmentally sensitive areas, and administrative boundaries in GIS, the spatial distributions of construction areas, equipment installation areas, and operating facilities can be clearly identified, thereby determining the specific physical impact ranges of activities in each stage.

[0083] For the construction stage, through the integration of BIM and GIS, demarcate areas such as the construction site, material stacking area, equipment operation area, and transportation routes. These areas directly generate carbon emissions from mechanical operations, energy consumption, and material transportation. For the operation stage, based on traffic flow, energy consumption data, and the distribution of on-site facilities, use GIS spatial analysis to extract the emission impact areas of vehicle exhaust, lighting, and power supply systems. In the demolition stage, determine the carbon emission diffusion range based on the demolition operation area and waste treatment site. Through methods such as spatial overlay and buffer analysis, visually present the physical impact ranges of carbon emissions in each stage in graphical form.

[0084] According to the organizational structure and management division of the project, match the defined physical impact ranges with the actual management responsibilities. Using the GIS platform, overlay the administrative division information of the project location and the internal zoning information of the project to clarify the emission responsibility subjects (such as construction units, operation management units, and demolition treatment units) in each area, forming carbon emission accounting areas with clear responsibilities and corresponding rights and responsibilities.

[0085] S13. Construct a carbon flow transfer matrix between each stage to quantify the transfer effect of carbon emissions in each stage.

[0086] Specifically, constructing a carbon flow transfer matrix requires clarifying the main carbon emission sources in each stage (construction, operation, demolition). For example, the construction stage includes carbon emissions during the operation of construction machinery, material production, and transportation; the operation stage involves carbon emissions during daily energy consumption, vehicle exhaust, and maintenance; the demolition stage focuses on carbon emissions during equipment disassembly, waste treatment, and resource recovery. Through on-site monitoring, historical data, and engineering models, calculate the total direct and indirect emissions in each stage respectively to provide a quantitative basis for constructing the transfer matrix.

[0087] Analyze the interactions between each stage. For example, the carbon embedded in materials during the construction stage may be released during the operation stage through repair and reuse processes, or a part of the embedded carbon may be recovered during the demolition stage, thereby reducing the overall emissions. Construct matrix M, where each element M ij represents the carbon emission transfer ratio from stage i to stage j. The transfer coefficient can be expressed by the formula:

[0088]

[0089] In the formula, Ei represents the total carbon emissions in stage i; ΔE ij represents the carbon emissions from stage i to stage j; the transfer coefficients are determined by fitting using statistical analysis, regression models or machine learning methods (such as random forests, neural networks).

[0090] Adopt a multi-source data acquisition method, utilize engineering monitoring data, sensor real-time data and simulation data to obtain the actual emission situation and transfer effect of each stage. Through data fusion and error correction, the transfer coefficients are dynamically adjusted to ensure that the matrix reflects the real engineering operation state. In addition, cross-validation and historical data review are regularly adopted to calibrate and update the transfer matrix.

[0091] Finally, couple and calculate the carbon emission data of each stage with the transfer matrix to simulate the overall carbon flow process. For example, calculate the cumulative carbon emissions of each stage throughout the life cycle through matrix multiplication, so as to realize the closed-loop accounting of carbon emissions throughout the life cycle. This matrix is not only used to quantify the direct transfer effect between stages, but also can identify errors caused by double counting or omission, ensuring that the accounting results have high accuracy and comparability.

[0092] S2. Set carbon emission accounting indicators for all types and collect multi-modal data corresponding to each stage.

[0093] In the description of the present invention, the acquisition of multi-modal data for each stage includes the following aspects:

[0094] 1. Data acquisition during the construction period

[0095] 1.1. Intelligent construction machinery: Install a Beidou terminal + 5G module to transmit fuel consumption (CAN bus direct reading, accuracy ±1.2%) and operation trajectory (generate a carbon emission intensity heat map) in real time.

[0096] 1.2. BIM model parsing: Extract the building material usage (reinforcement / concrete error < 2%) through the IFC standard.

[0097] 2. Operation period monitoring network

[0098] 2.1. ETC enhanced system (Electronic Toll Collection system): Deploy an AI coprocessor (FPGA acceleration) at the gantry to realize vehicle type recognition (ResNet-50 model, accuracy > 97%) and instantaneous emission calculation (improved COPERT model, resolution 0.1 second).

[0099] 2.2. Distributed optical fiber sensing: Install DAS nodes (Distributed Antenna System nodes) every 500m to monitor axle load (back-calculate the rolling resistance coefficient) and road surface deformation (predict emissions caused by maintenance requirements).

[0100] 3. Demolition Phase Traceability System

[0101] 3.1 UAV Cluster Modeling: Use UAVs equipped with LiDAR and SLAM algorithms to reconstruct the demolition site (point cloud density > 2000 points / m 2 ), and classify waste types through deep learning (concrete / asphalt classification accuracy > 93%).

[0102] 3.2 Blockchain Carbon Passport: Use Hyperledger Fabric (an open-source blockchain distributed ledger) to record the energy consumption of material crushing (smart meter data on the chain) and the transportation trajectory of recycled materials (connected to the API of the freight platform) on the chain.

[0103] S3. Build a hierarchical computing architecture based on edge-cloud collaborative technology, calculate the carbon emissions at each stage, and use a virtual road model that can be updated through online learning to verify the carbon emission calculation results.

[0104] In the description of the present invention, building a hierarchical computing architecture based on edge-cloud collaborative technology, calculating the carbon emissions at each stage, and using a virtual road model that can be updated through online learning to verify the carbon emission calculation results includes:

[0105] S31. Build a hierarchical computing architecture composed of an edge layer, a fog layer, and a cloud layer, and deploy them in sequence on the construction machinery side, the section management center, and the traffic control platform to achieve full-life cycle calculation of the highway.

[0106] Specifically, based on the edge-fog-cloud collaborative hierarchical computing architecture, this architecture is deployed in sequence on the construction machinery side, the section management center, and the traffic control platform, so as to realize real-time calculation and monitoring of key indicators such as carbon emissions and energy consumption in the full life cycle (construction, operation, demolition) of the highway.

[0107] 1. Edge Layer Deployment (Construction Machinery Side):

[0108] Deploy terminal devices such as sensors, GPS, and energy consumption monitoring devices at the construction site and on the construction machinery to collect data such as the operation status, fuel consumption, and equipment location of the construction machinery in real time. These data directly reflect the dynamic information of the construction site and are the basis for subsequent data processing and carbon emission calculation. The edge layer has the functions of preliminary data cleaning and preprocessing, can format and denoise the original data, and send the data to the upper-layer platform through a security protocol.

[0109] 2. Fog Layer Deployment (Section Management Center):

[0110] Build a fog computing platform at the section management center as an intermediate aggregation and processing node for edge data. The fog layer mainly undertakes the aggregation, rapid response, and preliminary analysis of local data. It further integrates the preprocessed data from each construction machinery terminal, conducts local event detection, real-time monitoring, and some simple carbon emission calculations, thereby reducing data transmission latency and improving the emergency handling ability within the region.

[0111] 3. Deployment of the cloud layer (traffic control platform):

[0112] Deploy a cloud computing center on the traffic control platform, and use high-performance computing resources and big data platforms to comprehensively integrate and deeply analyze the data from each section management center. The cloud layer performs full-life cycle model calculations, adopts a variety of accounting algorithms, data fusion, and simulation means to conduct comprehensive carbon emission and energy consumption analysis on the construction, operation, and demolition stages of the highway, and supports long-term trend prediction and dynamic optimization.

[0113] Through real-time data collection at the edge layer, local data processing at the fog layer, and deep integration and calculation at the cloud layer, the entire hierarchical architecture realizes fine monitoring and accounting of the full life cycle of the highway, providing real-time and accurate data support and decision-making basis for low-carbon construction and operation management.

[0114] S32. Use the hierarchical computing architecture to calculate the total construction carbon emissions during the construction stage.

[0115] In the description of the present invention, using the hierarchical computing architecture to calculate the total construction carbon emissions during the construction stage includes:

[0116] S321. Divide the multi-modal data during the construction stage into different construction emission types, and extract the corresponding accounting indicators. The construction emission types include equipment operation type, building material production type, and transportation type.

[0117] S322. Use the edge layer to calculate the single-machine carbon emissions of each construction emission type during the construction stage.

[0118] Specifically, during the construction process, various construction machinery (such as excavators, pavers, bulldozers, etc.) consume fuel or electricity during operation, and fuel combustion or electricity use will cause carbon emissions. Therefore, the carbon emissions of construction equipment are mainly calculated through their energy consumption. For fuel-driven equipment, the carbon emissions depend on the fuel consumption of the equipment, including fuel type, equipment power, operation time, and load conditions. Generally speaking, the fuel consumption of the equipment under full load, half load, or no load is different, so it is necessary to comprehensively consider the influence of the load rate to ensure the accuracy of the calculation.

[0119] For electric-driven equipment, it is necessary to consider the power consumption of the equipment and calculate it in combination with the carbon emission factor of the local power grid. Since the energy structures of power grids in different regions are different, for example, using thermal power, wind power or hydropower, the carbon emissions per unit of electric energy are also different. Therefore, local power data needs to be matched during the calculation. The carbon emissions of construction equipment mainly depend on the characteristics of fuel combustion. When fuel-driven equipment is in operation, its emissions are related to the combustion efficiency and chemical composition of the fuel. Different types of fuel (such as diesel and gasoline) will produce different carbon dioxide emissions when burned. For electric-driven equipment, although it does not directly produce carbon emissions itself, the electric energy used comes from the power grid, and the power generation method of the power grid (such as coal power, nuclear power, wind power, etc.) determines its carbon emission level. Therefore, the carbon emission calculation of electric-driven equipment needs to be corrected in combination with the local power structure.

[0120] In addition, when the equipment is actually in operation, it does not always operate at the rated power, but is affected by the load changes. Therefore, a load factor needs to be introduced during the calculation to reflect the actual fuel consumption or power consumption of the equipment under different working conditions, so as to improve the calculation accuracy.

[0121] The production of building materials is an important source of carbon emissions in highway construction, especially high-energy-consuming materials such as cement, steel bars and asphalt. During carbon emission accounting, the consumption of materials and the carbon emission factors in the production process are mainly considered. By counting various building materials required during the construction process and combining the production carbon emission data of each material, the total carbon emissions can be calculated.

[0122] The carbon emission factors of building materials usually come from the Life Cycle Assessment (LCA) database or industry statistical data. For example, the production of cement involves a high-temperature calcination process, releasing a large amount of carbon dioxide; a large amount of energy is also consumed during the smelting process of steel. Therefore, there are significant differences in the production emission levels of different materials, and calculations need to be carried out in combination with specific material types.

[0123] The carbon emissions of building materials mainly come from the extraction of raw materials, processing, energy consumption during production, and chemical reactions. For example, during the production of cement, limestone releases carbon dioxide when calcined at high temperatures, while steel smelting involves coal combustion and oxidation reactions. Therefore, each building material has a specific carbon emission factor, which can be used to estimate the carbon emission level during its production process.

[0124] S323. Use the fog layer to unify the mechanical trajectories of construction machinery during the construction stage with the building information model coordinates, calibrate the clocks of various devices, and integrate and calculate the total construction carbon emissions during the construction stage.

[0125] S324. Use the cloud layer to match the factor libraries of construction machinery and building materials, dynamically update the edge layer and the fog layer, and monitor the abnormal accounting data existing in the edge layer and the fog layer in real time.

[0126] S33. Calculate the total operating carbon emissions at the road network level during the operation phase using a hierarchical computing architecture.

[0127] In the description of the present invention, calculating the total operating carbon emissions at the road network level during the operation phase using a hierarchical computing architecture includes:

[0128] S331. Divide the multi-modal data in the operation phase into different operation emission types, and extract the corresponding accounting indicators. The operation emission types include transportation vehicle types and facility maintenance types.

[0129] S332. Use the edge layer to preprocess the multi-modal data, and extract the non-stop toll collection data, mobile phone signaling data, and road surface monitoring data of transportation vehicles in each accounting indicator.

[0130] Specifically, the edge layer is deployed at the ETC gantry and road surface monitoring nodes, and the multi-modal data is processed in real time through an embedded AI chip (such as NVIDIA Jetson Xavier): the lightweight YOLOv5 model is run at the ETC gantry end to achieve vehicle type classification (accuracy > 98%), and the single vehicle travel time and instantaneous speed are calculated by combining the license plate recognition result and the transaction timestamp.

[0131] The mobile phone signaling data is accessed through a 5G CPE (terminal device) device, and the kernel density estimation algorithm is used to generate a spatial heat map to supplement the traffic flow distribution of sections not covered by ETC; after the strain waveform data of the road surface monitoring optical fiber is denoised by wavelet transform, it is input into a pre-trained neural network model (input layer 64 nodes, hidden layer 32 nodes) to back-calculate the vehicle axle weight and rolling resistance coefficient. The edge node finally outputs a structured data packet (including fields such as timestamp, position coordinates, vehicle type, speed, axle weight, etc.), and encrypts and transmits it to the fog layer through the MQTT protocol.

[0132] S333. Use the fog layer to integrate the electronic non-stop toll collection data and mobile phone signaling data, generate a traffic flow matrix at the minute level, calculate the traffic flow carbon emissions, and combine with the calculated road surface maintenance carbon emissions to generate the total operating carbon emissions during the operation phase of a single expressway.

[0133] Specifically, it is completed at the section-level fog computing node. First, the ETC and mobile phone signaling data are aligned in time and space: the two data sources are fused based on the Kalman filter algorithm to eliminate the device clock deviation (error < 1 second) and positioning drift (spatial error < 10 meters), and a traffic flow matrix at the minute level (dimension: time × section × vehicle type × speed interval) is generated;

[0134] Subsequently, the dynamic emission factor library (synchronize the grid carbon intensity data every hour) is called, and the improved MOVES model is used to calculate the carbon emission intensity of each cell. The formula is:

[0135] E cell = ∑(N veh × EF speed × D route );

[0136] Wherein, N veh represents the number of vehicles, EF speed represents the speed-dependent emission factor; D route represents the road section length). At the same time, the prediction results of the fog layer integrated pavement degradation model (calculating the maintenance demand period based on the Paris fatigue crack propagation formula) are combined with the Internet of Things data of maintenance machinery (such as the GNSS trajectory of the roller and the diesel consumption curve) to quantify the carbon emissions of activities such as snowmelt agent spreading and crack repair. Finally, the traffic flow emissions and maintenance emissions are accumulated to generate the total carbon emissions during the operation period of a single expressway, and the key parameters of the accounting process are recorded through the blockchain to ensure audit traceability.

[0137] S334. Use the cloud layer for microscopic traffic simulation, simulate the correlation curve between the congestion index and emissions, and calculate the carbon emissions of the entire road network through network-level integrated parallel computing.

[0138] Specifically, it is executed by the cloud high-performance computing cluster. First, import real-time traffic flow data to drive the vehicle following model (IDM model parameters: maximum acceleration 2.6 m / s 2 , safety distance 2 seconds), simulate the vehicle start-stop and lane-changing behaviors under different congestion indices (0-1 continuous values), and generate a cluster of speed-emission relationship curves; use the MapReduce parallel framework to divide the entire road network into 1 km × 1 km calculation units, deploy independent simulation instances in each unit (a total of several concurrent processes), and dynamically adjust the emission factors in combination with meteorological data (temperature and wind speed fields output by the WRF model).

[0139] Finally, aggregate the results of each unit through the Reduce operation, and output a hypercube dataset of the carbon emissions of the entire road network including the spatio-temporal dimension (longitude, latitude, time slice) and the attribute dimension (vehicle type, fuel type, emission type), supporting multi-dimensional analysis and visual presentation, and the computing efficiency reaches millions of vehicle trajectory data processed per minute.

[0140] S34. Use a hierarchical computing architecture to calculate the total demolition carbon emissions during the demolition stage and perform full-life cycle integration.

[0141] In the description of the present invention, using a hierarchical computing architecture to calculate the total demolition carbon emissions during the demolition stage and perform full-life cycle integration includes:

[0142] S341. Divide the multi-modal data in the demolition stage into different demolition emission types, extract the corresponding accounting indicators, and the demolition emission types include demolition equipment types and waste treatment types.

[0143] S342. Identify and record the waste data existing on the highway and the usage data of the demolition equipment by using the edge layer.

[0144] S343. Use the fog layer to generate a unique digital ID for each batch of recycled waste, record the transportation distance, treatment process and reuse project of the waste, and calculate the total demolition carbon emissions during the demolition stage.

[0145] S344. Use the cloud layer to perform circular economy offset calculations, integrate and calculate the carbon emission distribution and total carbon emissions of the entire life cycle of the highway, store the output results of each layer in the cloud, and record the source, processing path and quality label of each piece of data through data lineage tracking.

[0146] S35. Construct a digital twin-based virtual highway model, introduce an incremental online learning mechanism, integrate the calculation data of each layer in the hierarchical calculation architecture, and achieve cross-stage and cross-time-space coupling simulation.

[0147] In the description of the present invention, constructing a digital twin-based virtual highway model, introducing an incremental online learning mechanism, integrating the calculation data of each layer in the hierarchical calculation architecture, and achieving cross-stage and cross-time-space coupling simulation include:

[0148] S351. Combine geographic information system, building information model and multi-physics field coupling to construct a digital twin-based virtual highway model, and integrate the output data of the hierarchical calculation architecture.

[0149] S352. Embed an incremental online learning module in the virtual highway model, regularly update the edge and cloud data, and adjust and correct the model parameters in the virtual highway model.

[0150] Specifically, embed an incremental online learning module in the digital twin model, enable the model to continuously self-update, adjust the parameters according to the newly collected data, and achieve real-time prediction and feedback.

[0151] For the online learning algorithm design, online gradient descent or incremental machine learning algorithms can be used to update the model parameters in real time. For example, let the model parameter be θ, and the new data sample be (x t , y t ), the update formula for online learning can be expressed as:

[0152]

[0153] In the formula, L(θ t ; x t , y t ) represents the current loss function (such as mean squared error), and α is the learning rate. This formula ensures that the model parameters can be quickly adjusted after receiving new data, reducing the prediction error.

[0154] The virtual highway model inputs new data from the edge and the cloud into the online learning module regularly or in real time; the online learning module uses the new data to fine-tune the parameters of key sub-models (such as the carbon emission prediction model and the status monitoring model) in the digital twin model, without the need to train from scratch, realizing rapid adaptive updates.

[0155] S353. Use the virtual highway model to perform coupled simulations among different stages, regions, and time periods during the entire life cycle of the highway, and simulate the mutual relationships in different stages.

[0156] In the description of the present invention, using the virtual highway model to perform coupled simulations among different stages, regions, and time periods during the entire life cycle of the highway, and simulating the mutual relationships in different stages includes:

[0157] S3531. Establish state vectors for the construction stage, operation stage, and demolition stage respectively. An example of the coupling formula is:

[0158]

[0159] In the formula, X i (t) represents the state of stage i at time t; f i represents the evolution function within stage i, describing the dynamic changes of this stage itself; u i (t) represents the external input received by stage i; g ij represents the coupling influence function of other stage j on stage i, quantifying the transfer effect between different stages.

[0160] S3532. Introduce a multi-scale simulation module into the virtual highway model, and use the spatio-temporal coupling simulation algorithm to interactively fuse multi-modal data and calculation results of each stage and region.

[0161] S3533. The multi-scale simulation modules at each stage transfer data through a unified interface, adopt a hierarchical simulation strategy, integrate the local short-term dynamics and the global long-term trends, and achieve cross-time and space simulation.

[0162] S3534. Use the carbon emission data output by the hierarchical computing architecture as the true accounting value, compare it with the carbon emission prediction value of the coupled simulation of the virtual highway model, quantitatively evaluate the difference between the prediction value and the true accounting value, and feedback the difference value to the incremental online learning module to optimize the parameters of the virtual highway model.

[0163] S354. Generalize and adapt the virtual highway model by constructing a highway knowledge graph.

[0164] In the description of the present invention, generalizing and adapting the virtual highway model by constructing a highway knowledge graph includes:

[0165] S3541. Set a unified feature space, use the pre-trained model as a feature extractor, freeze the underlying network of the virtual highway model, and build a transfer learning framework.

[0166] Specifically, the generalization adaptation of the virtual highway model is achieved by constructing a highway knowledge graph. First, in step S3541, a unified feature space is set and a transfer learning framework is built, including standardizing various heterogeneous data (such as traffic flow, material properties, environmental parameters, etc.) involved in the entire life cycle of expressways, defining a unified feature vector containing core indicators such as average daily traffic volume, pavement condition index, temperature, humidity, etc., using a pre-trained deep neural network model (such as LSTM or graph convolutional network trained based on historical expressway project data) as a feature extractor, freezing the weights of its underlying network to retain the general representation ability of basic features, and only fine-tuning and adapting the top fully connected layer to form a transferable model architecture.

[0167] In this process, the partial freezing and parameter sharing mechanism of the network layer is implemented using Keras (an open-source artificial neural network library) or the PyTorch framework (an open-source deep learning framework for machine learning and deep learning), and the adaptation efficiency of the model to new projects is improved through a few-shot learning strategy (such as feature alignment based on contrastive learning).

[0168] S3542. Construct a highway knowledge graph, store highway prior knowledge, and automatically match similar historical cases when a new project is input to initialize the model parameters of the virtual highway model.

[0169] Specifically, a graph database (such as Neo4j graph database software) can be used to construct the highway knowledge graph to store entity nodes (including material types, construction techniques, climate zones, etc.) in the field of highway engineering and their association relationships, and structured knowledge is extracted from industry standard documents and engineering case libraries through natural language processing technology to establish a semantic network containing prior knowledge such as material performance parameters, typical structural designs, and regional emission factors.

[0170] When a new project is input, its engineering features (such as geographical coordinates, designed speed, pavement structure layer combination) are first parsed. The graph embedding algorithm (such as Node2Vec) is used to map the project features into the vector space of the knowledge graph, calculate the cosine similarity with the historical case nodes, and automatically match the past project cases whose topological structure similarity exceeds a threshold (usually set to 0.85). The model parameters (including neural network weights and emission factor library data) trained for the corresponding cases are extracted as the initialization parameters of the new model. At the same time, the graph attention mechanism (GAT) is used to aggregate the feature information of adjacent nodes, and the initialization parameters are dynamically adjusted to adapt to the regional characteristic differences (such as the impact of atmospheric oxygen content in plateau areas on mechanical combustion efficiency). Finally, a virtual simulation model applicable to highway projects with different climate conditions and traffic grades can be quickly deployed without re-training.

[0171] S4. Draw a carbon footprint heat map based on the carbon emission accounting results to show the spatio-temporal evolution process.

[0172] Specifically, the carbon emission data collected from the hierarchical computing architecture (edge-fog-cloud), including the carbon emission information in the construction, operation, and demolition stages. Combining with the geographical information system (GIS) data of the highway, the carbon emission accounting data is mapped to the road grid (such as a rasterized area of 100m×100m). Interpolation algorithms (such as Kriging interpolation, inverse distance weighted IDW) are used to fill in the missing data to ensure the spatial continuity of carbon emissions. The geographical weighted regression (GWR) method is used to calculate the carbon emission intensity of each spatial unit. Visualization tools, such as Matplotlib, Seaborn, Plotly or Kepler.gl, etc., are used to draw the carbon footprint heat map, and the carbon emission intensity is displayed using a color gradient (blue-green-yellow-red).

[0173] The GIS spatio-temporal interpolation technology is used to generate dynamic charts of the carbon footprint (such as dynamic layers, heat animations). Through the time slider function, the visualization playback of the carbon footprint over time is realized, and the spatio-temporal distribution changes of carbon emissions in different stages are analyzed. In addition, the K-Means clustering or DBSCAN density clustering method can be used to identify the high-value areas (hot spots) of carbon emissions. Combining with the road topological structure, the key influencing factors of carbon emissions, such as traffic flow density, construction energy consumption, transportation distance, etc., are analyzed. Optimization measures, such as construction energy consumption control, road network optimization, intelligent traffic scheduling, etc., are proposed for high-carbon emission areas. Combining with real-time monitoring data, dynamic carbon emission management is realized, and the carbon emission intensity in the whole life cycle of the highway is gradually reduced.

[0174] In summary, by means of the above technical solutions of the present invention, the present invention covers the construction, operation, and demolition phases in the whole life cycle of expressways, ensuring the comprehensiveness and systematicness of the accounting results; adopting multiple data sources and collection methods, and combining corresponding accounting methods for calculation, ensuring the accuracy and reliability of the accounting results; at the same time, providing detailed accounting processes and steps, facilitating actual operation and application, and providing a scientific basis for the low-carbon construction and operation of expressways.

[0175] By dividing the whole life cycle of expressways into construction, operation, and demolition phases, dynamically calibrating the accounting boundaries of each phase based on the spatio-temporal dimension, the refined management of carbon emissions throughout the whole process and all time periods is realized; adopting the dynamic boundary correction technology can accurately capture the project progress and environmental changes, ensuring the timeliness and representativeness of carbon emission data in each phase, thus breaking through the limitations of the traditional method with a single stage division and incomplete data collection, providing a scientific basis for green construction and low-carbon operation, not only significantly improving the accuracy and credibility of the accounting results, but also providing data support for the subsequent optimization of carbon emission reduction strategies and environmental impact assessment.

[0176] By setting all types of carbon emission indicators and collecting multi-modal data corresponding to each phase, the efficient integration of various types of information is realized. With the edge-cloud collaborative hierarchical computing architecture, it can process on-site sensing and historical data in real time, and use data fusion algorithms to eliminate the differences brought by a single accounting method; at the same time, the virtual highway model with online learning and updating dynamically verifies and self-corrects the calculation results, ensuring that the accounting results of each phase reach a high level in terms of accuracy and comparability, thus effectively reducing data noise and errors, and improving the scientificity and adaptability of the whole life cycle carbon emission accounting.

[0177] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the indication of the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps does not have a strict order limit, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily have to be executed at the same moment, but can be executed at different moments, and their execution order does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

Claims

1. A method for carbon emission statistics and accounting throughout the life cycle of an expressway, characterized in that Including: S1. Divide the whole life cycle of the highway into multiple stages, and dynamically calibrate the accounting boundary of each stage based on the spatio-temporal dimension; S2. Set carbon emission accounting indicators of all types, and collect multi-modal data corresponding to each stage; S3. Build a hierarchical computing architecture based on edge-cloud collaborative technology, calculate the carbon emissions of each stage, and use a virtual highway model that can be updated by online learning to verify the carbon emission accounting results; S4. Draw a carbon footprint heat map based on the carbon emission accounting results to show the spatio-temporal evolution process.

2. The method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 1, wherein The dividing the whole life cycle of the highway into multiple stages and dynamically calibrating the accounting boundary of each stage based on the spatio-temporal dimension includes: S11. Divide the whole life cycle of the highway into construction stage, operation stage and demolition stage, and dynamically adjust the duration of each stage according to the actual progress of the project; S12. Use highway engineering information combined with geographic information system and building information model to define the physical impact range and emission responsibility area of carbon emissions in each stage; S13. Build a carbon flow transfer matrix between each stage to quantify the transfer effect of carbon emissions in each stage.

3. A method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 2, characterized in that, The dynamically adjusting the duration of each stage according to the actual progress of the project includes: S111. Obtain the building information model and construction machinery data of the highway project, divide the highway construction area into several cell grids, and generate a machinery coverage matrix; S112. Compare the actual coverage grid of the highway with the designed grid, calculate the real-time progress, and use a long short-term memory network to predict the future construction progress. When the construction progress is greater than the preset progress threshold, switch the highway from the construction stage to the operation stage, and mark the construction and operation time information; S113. Obtain the pavement performance index of the highway. When the pavement performance index is lower than the preset performance threshold, switch the highway from the operation stage to the demolition stage, and mark the demolition time information.

4. A method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 1, characterized in that, The building a hierarchical computing architecture based on edge-cloud collaborative technology, calculating the carbon emissions of each stage, and using a virtual highway model that can be updated by online learning to verify the carbon emission accounting results includes: S31. Build a hierarchical computing architecture composed of an edge layer, a fog layer and a cloud layer, and deploy them in turn on the construction machinery side, the section management center and the traffic control platform to realize the whole life cycle calculation of the highway; S32. Use the hierarchical computing architecture to calculate the total construction carbon emissions in the construction stage; S33. Use the hierarchical computing architecture to calculate the total operation carbon emissions at the road network level during the operation stage; S34. Use the hierarchical computing architecture to calculate the total demolition carbon emissions during the demolition stage and conduct whole life cycle integration; S35. Build a virtual highway model based on digital twin, introduce an incremental online learning mechanism, integrate the calculation data of each layer in the hierarchical computing architecture, and realize cross-stage and cross-spatio-temporal coupled simulation.

5. A method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 4, characterized in that, The using the hierarchical computing architecture to calculate the total construction carbon emissions in the construction stage includes: S321. Divide the multi-modal data in the construction stage into different construction emission types, and extract the corresponding accounting indicators. The construction emission types include equipment operation type, building material production type and transportation type; S322. Use the edge layer to calculate the single-machine carbon emissions of each construction emission type in the construction stage; S323. Unify the mechanical trajectories of construction machinery during the construction phase with the building information model coordinates using the fog layer, calibrate the clocks of various devices, and integrate and calculate the total construction carbon emissions during the construction phase; S324. Use the cloud layer to match the factor libraries of construction machinery and building materials, dynamically update the edge layer and the fog layer, and monitor the abnormal accounting data existing in the edge layer and the fog layer in real time.

6. The carbon emission statistical accounting method for the whole life cycle of an expressway according to claim 4, characterized in that, The calculation of the total operation carbon emissions at the road network level during the operation phase using the hierarchical calculation architecture includes: S331. Divide the multimodal data in the operation phase into different operation emission types, and extract the corresponding accounting indicators. The operation emission types include transportation vehicle types and facility maintenance types; S332. Use the edge layer to preprocess the multimodal data, and extract the non-stop toll collection data, mobile phone signaling data, and road surface monitoring data of transportation vehicles in each accounting indicator; S333. Use the fog layer to integrate the electronic non-stop toll collection data and mobile phone signaling data, generate a traffic flow matrix at the minute level, calculate the carbon emissions of traffic flow, and combine with the calculated carbon emissions of road surface maintenance to generate the total operation carbon emissions of a single expressway during the operation phase; S334. Use the cloud layer to perform microscopic traffic simulation, simulate the correlation curve between the congestion index and emissions, and calculate the carbon emissions of the entire road network through parallel integration at the road network level.

7. A method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 4, characterized in that The calculation of the total demolition carbon emissions during the demolition phase using the hierarchical calculation architecture and the full life cycle integration include: S341. Divide the multimodal data in the demolition phase into different demolition emission types, and extract the corresponding accounting indicators. The demolition emission types include demolition equipment types and waste treatment types; S342. Use the edge layer to identify and record the waste data existing on the expressway and the usage data of demolition equipment; S343. Use the fog layer to generate a unique digital ID for each batch of recycled waste, record the transportation distance, treatment process, and reuse project of the waste, and calculate the total demolition carbon emissions during the demolition phase; S344. Use the cloud layer to perform circular economy offset calculation, integrate and calculate the carbon emission distribution and total carbon emissions of the full life cycle of the expressway, store the output results of each layer in the cloud, and record the source, processing path, and quality label of each piece of data through data lineage tracking.

8. A method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 4, characterized in that, The construction of a digital twin-based virtual highway model, introducing an incremental online learning mechanism, integrating the calculation data of each layer in the hierarchical calculation architecture, and realizing cross-phase and cross-time-space coupling simulation include: S351. Combine the geographic information system, building information model, and multi-physical field coupling to construct a digital twin-based virtual highway model, and integrate the output data of the hierarchical calculation architecture; S352. Embed an incremental online learning module in the virtual highway model, regularly update the edge and cloud data, and adjust and correct the model parameters in the virtual highway model; S353. Use the virtual highway model to perform coupling simulation between different stages, regions, and time periods during the full life cycle of the expressway, and simulate the mutual relationship between different stages; S354. Generalize and adapt the virtual highway model by constructing a highway knowledge graph.

9. A method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 8, characterized in that The coupling simulation between various stages, regions, and time periods within the entire life cycle of an expressway using a virtual highway model, and the simulation of the mutual relationships in different stages include: S3531. Establish state vectors for the construction stage, operation stage, and demolition stage respectively; S3532. Introduce a multi-scale simulation module into the virtual highway model, and use a spatio-temporal coupling simulation algorithm to interactively integrate multi-modal data and calculation results of each stage and region; S3533. In the multi-scale simulation module of each stage, data is transmitted through a unified interface, and a hierarchical simulation strategy is adopted to integrate local short-term dynamics and global long-term trends to achieve cross-time and space simulation; S3534. Take the carbon emission data output by the hierarchical calculation framework as the true accounting value, compare it with the carbon emission prediction value of the virtual highway model coupling simulation, quantitatively evaluate the difference between the prediction value and the true accounting value, and feedback the difference value to the incremental online learning module to optimize the parameters of the virtual highway model.

10. A method for statistical accounting of carbon emissions throughout the life cycle of an expressway according to claim 8, characterized in that, The general adaptation of the virtual highway model by constructing a highway knowledge graph includes: S3541. Set a unified feature space, use a pre-trained model as a feature extractor, freeze the underlying network of the virtual highway model, and build a transfer learning framework; S3542. Construct a knowledge graph of expressways, store prior knowledge of highways, and automatically match similar historical cases when a new project is input to initialize the model parameters of the virtual highway model.

Images