A zero-carbon highway full-cycle intelligent management method and system and medium

Abstract

This application provides a method, system, and medium for intelligent management of the entire lifecycle of zero-carbon highways. The method includes: acquiring heterogeneous multi-source time-series data of highways, processing it to construct a dynamic highway lifecycle carbon footprint knowledge graph, deconstructing and splitting it; obtaining a hierarchical highway lifecycle carbon footprint standard dataset to construct a prediction model; obtaining a carbon energy prediction dataset and anomaly tracing and identification result set to construct a zero-carbon highway multi-objective collaborative optimization scheduling model; solving this model to obtain the globally optimal scheduling strategy and intelligent decision-making scheme; and achieving intelligent processing of zero-carbon highway lifecycle data, refined carbon footprint accounting, anomaly tracing, and low-carbon optimization decision-making through closed-loop iteration of full-lifecycle multi-source data acquisition and time-series benchmark anchoring, multi-dimensional data cleaning and carbon energy coupling and fusion, dynamic carbon footprint knowledge graph and hierarchical deconstruction, full-cycle carbon energy time-series prediction and anomaly tracing and identification, and zero-carbon highway multi-objective optimization scheduling and full-cycle intelligent decision-making.

Description

Technical Field

[0001] This application relates to the fields of intelligent management and control of zero-carbon highways, big data processing throughout the entire life cycle, carbon footprint accounting and intelligent decision-making technology. Specifically, it relates to a method, system and medium for intelligent management of zero-carbon highways throughout their entire life cycle. Background Technology

[0002] Zero-carbon highways have become the core development direction for highway construction and operation. Currently, existing highway carbon energy consumption management generally has limitations, often focusing only on data statistics for a single stage of construction or operation, failing to cover the entire lifecycle from planning, construction, operation, and decommissioning. Data from various sensing devices, engineering systems, and operation platforms is multi-source and heterogeneous, lacking a unified spatiotemporal benchmark, sampling granularity, unit of measurement, and coding standards. Data cannot be interconnected and linked. Raw time-series monitoring data is susceptible to environmental interference, equipment drift causing jumps and anomalies, noise redundancy, and time-series breakpoints. Traditional fixed-threshold cleaning methods have low accuracy, making it difficult to establish a reliable energy consumption-carbon emission coupling relationship. There is a lack of standardized carbon footprint modeling architecture, hindering the realization of multi-element coupling topological association, carbon link hierarchical deconstruction, and dynamic weight updates. Carbon emissions and energy supply and demand are mostly based on static statistics, lacking intelligent time-series prediction, adaptive anomaly identification, and source tracing capabilities. Existing control decisions are mostly based on experience-based manual scheduling, lacking multi-objective collaborative optimization mechanisms and a data closed-loop iterative process, thus failing to support dynamic, intelligent, and low-carbon management throughout the entire lifecycle of zero-carbon highways. Summary of the Invention

[0003] The purpose of this application is to provide a method, system and medium for intelligent management of the entire life cycle of zero-carbon highways, which can realize intelligent processing of data throughout the entire life cycle of zero-carbon highways, refined accounting of carbon footprint, anomaly tracing and low-carbon optimization decision-making.

[0004] This application also provides a method for intelligent management of zero-carbon highways throughout their entire lifecycle, including the following steps: Obtain heterogeneous multi-source time-series data of highways and perform preprocessing to obtain a standardized spatiotemporal raw dataset of highways throughout their entire lifecycle. The original spatiotemporally standardized dataset of the entire life cycle of the expressway is processed to obtain a high-quality time-series dataset of the entire life cycle of the expressway, which is then fused to obtain a carbon-energy coupling fusion dataset of the entire life cycle of the expressway. Based on the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a dynamic highway lifecycle carbon footprint knowledge graph is constructed and deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset. Based on the hierarchical highway full life cycle carbon footprint standard dataset, a time series prediction model is constructed to obtain a carbon energy time series prediction dataset and compare it to obtain a multi-dimensional anomaly tracing and identification result set. Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed and solved to obtain the globally optimal scheduling strategy and intelligent decision-making scheme.

[0005] Optionally, in the zero-carbon highway full-lifecycle intelligent management method described in this application embodiment, the step of acquiring heterogeneous multi-source time-series data of the highway and performing preprocessing to obtain a standardized spatiotemporal raw dataset of the highway full-lifecycle includes: Acquire heterogeneous multi-source time-series data of highways, including planning and design parameter data, building material production and transportation ledger data, construction energy consumption and emission monitoring data, roadside new energy power generation and supply data, road network traffic flow perception data, tunnel electromechanical operation and maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling and resource utilization data. Time series processing is performed on the heterogeneous multi-source time series data of the expressway to obtain standard expressway time series multi-source data. Mapping the time-series multi-source data of the standard highway to obtain spatiotemporal multi-source data of the standard highway; The standard highway spatiotemporal multi-source data is preprocessed to obtain a standardized original dataset of the highway throughout its entire lifecycle.

[0006] Optionally, in the zero-carbon highway full-lifecycle intelligent management method described in this application embodiment, the step of processing the highway full-lifecycle spatiotemporally standardized original dataset to obtain a high-quality highway full-lifecycle time-series dataset and then fusing it to obtain a highway full-lifecycle carbon-energy coupled fusion dataset includes: Outlier removal is performed on the original spatiotemporally standardized dataset of the entire life cycle of the expressway to obtain a clean time-series dataset of the entire life cycle of the expressway. Denoising and dimensionality reduction are performed on the clean highway full life cycle time series dataset to obtain a low-dimensional highway full life cycle time series feature dataset. Time series completion is performed based on the low-dimensional highway full life cycle time series feature dataset to obtain a high-quality highway full life cycle time series dataset. By fusing the high-quality highway lifecycle time-series dataset, a highway lifecycle carbon-energy coupled fusion dataset is obtained.

[0007] Optionally, in the zero-carbon highway full-lifecycle intelligent management method described in this application embodiment, the step of constructing a dynamic highway full-lifecycle carbon footprint knowledge graph based on the highway full-lifecycle carbon-energy coupling and fusion dataset, and then deconstructing and splitting it to obtain a hierarchical highway full-lifecycle carbon footprint standard dataset includes: Based on the node and edge relationships of the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a knowledge graph of highway lifecycle carbon footprint is constructed. The knowledge graph of the carbon footprint of the entire life cycle of the expressway is corrected by a preset algorithm model to obtain a dynamic knowledge graph of the carbon footprint of the entire life cycle of the expressway. Based on the dynamic highway lifecycle carbon footprint knowledge graph, the data is deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset.

[0008] Optionally, in the zero-carbon highway full-lifecycle intelligent management method described in this application embodiment, the step of constructing a time-series prediction model based on the hierarchical highway full-lifecycle carbon footprint standard dataset, obtaining a carbon energy time-series prediction dataset and comparing it to obtain a multi-dimensional anomaly tracing and identification result set includes: Multi-dimensional impact features were extracted based on the hierarchical highway full life cycle carbon footprint standard dataset. The multi-dimensional influencing characteristics include road service life, pavement deterioration and damage level, traffic flow temporal fluctuation characteristics of road sections, seasonal climate conditions, and fluctuation coefficient of new energy power output in the road area. The multidimensional feature matrix is ​​obtained by processing the dimensional influence features in conjunction with the hierarchical highway full life cycle carbon footprint standard dataset. A time-series prediction model is constructed based on the multidimensional feature matrix to obtain a carbon energy time-series prediction dataset. An anomaly identification result set is obtained by comparing the carbon energy time series prediction dataset. Based on the anomaly identification result set, the location is determined to obtain a multidimensional anomaly tracing and identification result set.

[0009] Optionally, in the intelligent management method for the entire lifecycle of zero-carbon highways described in this application embodiment, the step of constructing and solving a multi-objective collaborative optimization scheduling model for zero-carbon highways based on the carbon energy time-series prediction dataset and the multi-dimensional anomaly source identification result set to obtain the globally optimal scheduling strategy and intelligent decision-making scheme includes: Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed. The zero-carbon high-speed multi-objective cooperative optimization scheduling model is solved by a preset algorithm to obtain the globally optimal scheduling strategy; The global optimal scheduling strategy includes a new energy regulation strategy, a load optimization allocation strategy, and a road network low-carbon management strategy. The intelligent decision-making scheme is obtained by processing the multidimensional anomaly tracing and identification result set. The intelligent decision-making schemes include intelligent road maintenance decision-making schemes, road area carbon sink optimization decision-making schemes, and low-carbon disposal decision-making schemes for decommissioned solid waste.

[0010] Secondly, embodiments of this application provide a zero-carbon highway full-lifecycle intelligent management system. This system includes a memory and a processor. The memory includes a program for a zero-carbon highway full-lifecycle intelligent management method. When the program for the zero-carbon highway full-lifecycle intelligent management method is executed by the processor, it implements the following steps: Obtain heterogeneous multi-source time-series data of highways and perform preprocessing to obtain a standardized spatiotemporal raw dataset of highways throughout their entire lifecycle. The original spatiotemporally standardized dataset of the entire life cycle of the expressway is processed to obtain a high-quality time-series dataset of the entire life cycle of the expressway, which is then fused to obtain a carbon-energy coupling fusion dataset of the entire life cycle of the expressway. Based on the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a dynamic highway lifecycle carbon footprint knowledge graph is constructed and deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset. Based on the hierarchical highway full life cycle carbon footprint standard dataset, a time series prediction model is constructed to obtain a carbon energy time series prediction dataset and compare it to obtain a multi-dimensional anomaly tracing and identification result set. Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed and solved to obtain the globally optimal scheduling strategy and intelligent decision-making scheme.

[0011] Optionally, in the zero-carbon highway full-lifecycle intelligent management system described in this application embodiment, the step of acquiring heterogeneous multi-source time-series data of the highway and performing preprocessing to obtain a standardized spatiotemporal raw dataset of the highway full-lifecycle includes: Acquire heterogeneous multi-source time-series data of highways, including planning and design parameter data, building material production and transportation ledger data, construction energy consumption and emission monitoring data, roadside new energy power generation and supply data, road network traffic flow perception data, tunnel electromechanical operation and maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling and resource utilization data. Time series processing is performed on the heterogeneous multi-source time series data of the expressway to obtain standard expressway time series multi-source data. Mapping the time-series multi-source data of the standard highway to obtain spatiotemporal multi-source data of the standard highway; The standard highway spatiotemporal multi-source data is preprocessed to obtain a standardized original dataset of the highway throughout its entire lifecycle.

[0012] Optionally, in the zero-carbon highway full-lifecycle intelligent management system described in this application embodiment, the step of processing the highway full-lifecycle spatiotemporally standardized original dataset to obtain a high-quality highway full-lifecycle time-series dataset and then fusing it to obtain a highway full-lifecycle carbon-energy coupled fusion dataset includes: Outlier removal is performed on the original spatiotemporally standardized dataset of the entire life cycle of the expressway to obtain a clean time-series dataset of the entire life cycle of the expressway. Denoising and dimensionality reduction are performed on the clean highway full life cycle time series dataset to obtain a low-dimensional highway full life cycle time series feature dataset. Time series completion is performed based on the low-dimensional highway full life cycle time series feature dataset to obtain a high-quality highway full life cycle time series dataset. By fusing the high-quality highway lifecycle time-series dataset, a highway lifecycle carbon-energy coupled fusion dataset is obtained.

[0013] Thirdly, embodiments of this application also provide a computer-readable storage medium, which includes a program for a zero-carbon highway full-cycle intelligent management method. When the program is executed by a processor, it implements the steps of the zero-carbon highway full-cycle intelligent management method as described in any of the above claims.

[0014] As can be seen from the above, the zero-carbon highway full-lifecycle intelligent management method, system, and medium provided in this application embodiment acquires heterogeneous multi-source time-series data of highways and preprocesses it to obtain a standardized original dataset of the highway's full-lifecycle time-series data. This dataset is then processed to obtain a high-quality highway full-lifecycle time-series dataset, which is then fused to obtain a highway full-lifecycle carbon-energy coupled fused dataset. A dynamic highway full-lifecycle carbon footprint knowledge graph is constructed based on this dataset and deconstructed and split to obtain a hierarchical highway full-lifecycle carbon footprint standard dataset. Finally, a time-series prediction model is constructed based on this hierarchical highway full-lifecycle carbon footprint standard dataset to obtain... A carbon energy time-series prediction dataset is obtained and compared to generate a multi-dimensional anomaly source identification result set. Based on the carbon energy time-series prediction dataset and the multi-dimensional anomaly source identification result set, a zero-carbon highway multi-objective collaborative optimization scheduling model is constructed and solved to obtain the globally optimal scheduling strategy and intelligent decision-making scheme. Through the full-domain acquisition of heterogeneous multi-source raw time-series data throughout the entire life cycle and unified anchoring of time-series benchmarks, deep cleaning of multi-dimensional data based on time-series differences and carbon energy coupling and fusion, construction and hierarchical deconstruction of dynamic carbon footprint knowledge graph, intelligent prediction of carbon energy time-series data throughout the entire life cycle and multi-dimensional anomaly source identification, and closed-loop iteration of zero-carbon highway multi-objective optimization scheduling and full-cycle intelligent decision-making, intelligent processing of zero-carbon highway full life cycle data, refined carbon footprint accounting, anomaly source tracing, and low-carbon optimization decision-making are realized.

[0015] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a zero-carbon highway full-lifecycle intelligent management method provided in this application embodiment; Figure 2 A flowchart illustrating the full-lifecycle heterogeneous multi-source raw time-series data acquisition and unified anchoring of time-series benchmarks for a zero-carbon highway intelligent management method provided in this application embodiment; Figure 3A high-level flowchart of a zero-carbon highway full-lifecycle intelligent management method provided in this application embodiment. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0019] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0020] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a zero-carbon highway full-lifecycle intelligent management method according to some embodiments of this application. This zero-carbon highway full-lifecycle intelligent management method is used in terminal devices, such as mobile phones and computers. The zero-carbon highway full-lifecycle intelligent management method includes the following steps: S11. Obtain heterogeneous multi-source time-series data of highways and perform preprocessing to obtain a standardized spatiotemporal raw dataset of the entire life cycle of highways. S12. Process the original spatiotemporal standardized dataset of the entire life cycle of the highway to obtain a high-quality time-series dataset of the entire life cycle of the highway, and then fuse it to obtain a carbon-energy coupling fusion dataset of the entire life cycle of the highway. S13. Construct a dynamic highway lifecycle carbon footprint knowledge graph based on the highway lifecycle carbon energy coupling and fusion dataset, and deconstruct and split it to obtain a hierarchical highway lifecycle carbon footprint standard dataset. S14. Construct a time-series prediction model based on the hierarchical highway full life cycle carbon footprint standard dataset, obtain carbon energy time-series prediction dataset and compare it to obtain a multi-dimensional anomaly tracing and identification result set. S15. Based on the carbon energy time series prediction dataset and the multi-dimensional anomaly source identification result set, construct a zero-carbon high-speed multi-objective collaborative optimization scheduling model and solve it to obtain the global optimal scheduling strategy and intelligent decision-making scheme.

[0021] This process involves acquiring and preprocessing heterogeneous multi-source time-series data of highways to obtain a standardized spatiotemporal dataset of the entire highway lifecycle. This standardized dataset is then processed to obtain a high-quality time-series dataset of the entire highway lifecycle, which is then fused to obtain a carbon-energy coupled fusion dataset of the entire highway lifecycle. Based on this dataset, a dynamic knowledge graph of the carbon footprint of the entire highway lifecycle is constructed, deconstructed, and split to obtain a hierarchical standard dataset of the carbon footprint of the entire highway lifecycle. Finally, a time-series prediction model is built based on this standard dataset, resulting in a carbon energy time-series prediction dataset, which is then compared to obtain multiple... The system utilizes a multi-dimensional anomaly source identification result set to construct and solve a zero-carbon highway multi-objective collaborative optimization scheduling model based on the carbon energy time series prediction dataset and the multi-dimensional anomaly source identification result set. This yields the globally optimal scheduling strategy and intelligent decision-making scheme. Through the full-domain acquisition of heterogeneous multi-source raw time series data throughout the entire life cycle and unified anchoring of the time series benchmark, deep cleaning and carbon energy coupling fusion of multi-dimensional data based on time series difference, construction and hierarchical deconstruction of dynamic carbon footprint knowledge graph, intelligent prediction of carbon energy time series throughout the entire life cycle and multi-dimensional anomaly source identification, and closed-loop iteration of multi-objective optimization scheduling and intelligent decision-making throughout the entire life cycle of the zero-carbon highway, the system achieves intelligent processing of data throughout the entire life cycle of the zero-carbon highway, refined carbon footprint accounting, anomaly source tracing, and low-carbon optimization decision-making.

[0022] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the full-lifecycle heterogeneous multi-source raw time-series data acquisition and unified anchoring of time-series benchmarks for a zero-carbon highway full-lifecycle intelligent management method according to some embodiments of this application. According to embodiments of the present invention, the acquisition and preprocessing of heterogeneous multi-source time-series data of the highway to obtain a standardized spatiotemporal raw dataset for the entire highway lifecycle specifically involves: Acquire heterogeneous multi-source time-series data of highways, including planning and design parameter data, building material production and transportation ledger data, construction energy consumption and emission monitoring data, roadside new energy power generation and supply data, road network traffic flow perception data, tunnel electromechanical operation and maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling and resource utilization data. Time series processing is performed on the heterogeneous multi-source time series data of the expressway to obtain standard expressway time series multi-source data. Mapping the time-series multi-source data of the standard highway to obtain spatiotemporal multi-source data of the standard highway; The standard highway spatiotemporal multi-source data is preprocessed to obtain a standardized original dataset of the highway throughout its entire lifecycle.

[0023] This involves simultaneously acquiring heterogeneous multi-source time-series data from four stages of highway development—planning, construction, operation, and decommissioning—through a parallel acquisition method. This includes planning and design parameter data, building material production and transportation records, construction energy consumption and emission monitoring data, roadside renewable energy power generation data, road network traffic flow perception data, tunnel electromechanical maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling, and resource utilization data. All acquired heterogeneous multi-source time-series data is stamped with BeiDou UTC millisecond-level timestamps and road segment stationing spatial codes. Time-series resampling and alignment algorithms are used to eliminate time-series offsets caused by different terminals, sampling frequencies, and transmission delays, resulting in standard highway time-series multi-source data. This achieves precise alignment of data across the entire lifecycle on a unified timeline. Furthermore, a multi-source data spatial mapping method is used to integrate BIM 3D model data, IoT sensor time-series data, and other data. Human-machine inspection point cloud data, vehicle-mounted perception data, and maintenance ledger text data are uniformly mapped to the same spatiotemporal coordinate system through coordinate transformation and spatial matching algorithms. This yields standardized spatiotemporal multi-source data of highways that are uniquely correlated in spatial dimension, can be located, and can be retrieved. Carbon feature standardization coding methods are used to encode carbon features of carbon data sources, completing identification, classification, and calculable processing. Format normalization and desensitization encryption methods are used to unify fields, normalize units, and standardize dimensions of multi-source heterogeneous data. Sensitive data and key engineering information are hash-desensitized and symmetrically encrypted to complete data security processing. This results in a standardized spatiotemporal raw dataset of highways that is unified in spatiotemporal reference, standardized in format, correlateable, traceable, and calculable. This addresses the systemic defects of existing technologies, such as spatiotemporal misalignment of data across stages, stage fragmentation, inability to connect, and difficulty in full life-cycle carbon traceability, from the bottom layer of data processing.

[0024] According to an embodiment of the present invention, the step of processing the original spatiotemporally standardized dataset of the entire highway lifecycle to obtain a high-quality time-series dataset of the entire highway lifecycle and then fusing it to obtain a carbon-energy coupled fused dataset of the entire highway lifecycle specifically involves: Outlier removal is performed on the original spatiotemporally standardized dataset of the entire life cycle of the expressway to obtain a clean time-series dataset of the entire life cycle of the expressway. Denoising and dimensionality reduction are performed on the clean highway full life cycle time series dataset to obtain a low-dimensional highway full life cycle time series feature dataset. Time series completion is performed based on the low-dimensional highway full life cycle time series feature dataset to obtain a high-quality highway full life cycle time series dataset. By fusing the high-quality highway lifecycle time-series dataset, a highway lifecycle carbon-energy coupled fusion dataset is obtained.

[0025] Specifically, the entire lifecycle time-series dataset of highways was identified and anomalous jump points caused by sensor drift, network jitter, and equipment malfunctions were removed using first-order temporal difference and the 3σ criterion. After removing anomalous points, the dataset was rearranged according to the original timestamps to obtain a clean, anomalous highway lifecycle time-series dataset. Wavelet threshold denoising and principal component analysis were then used to process this clean dataset for dimensionality reduction, resulting in a low-dimensional, redundant highway lifecycle time-series feature dataset. Neighborhood correlation interpolation was then used to fill in the time-series breakpoints in the low-dimensional highway lifecycle time-series feature dataset, resulting in a high-quality highway lifecycle time-series dataset. This process achieved denoising, purification, and dimensionality reduction of high-dimensional carbon-related data. Based on this high-quality highway lifecycle time-series dataset, further... Energy consumption and carbon emissions are defined as follows: energy consumption includes photovoltaic power output, wind power output, equipment power consumption, fuel consumption, and transportation energy consumption; carbon emissions include carbon emissions from direct combustion, indirect carbon emissions from electricity use, carbon emissions from building materials, and carbon absorption by carbon sinks. A mapping table is established, linking various energy sources to their corresponding benchmark carbon emission characteristics. The cleaned energy consumption time-series data and carbon emission monitoring data are unified to the same time-series sampling granularity. Field association is performed by timestamp, road segment number, and time segment label. Energy consumption characteristics, carbon emission characteristics, road surface condition characteristics, and traffic flow characteristics are spliced ​​together to construct a fusion data table with a unified field structure and a unified spatiotemporal index. Finally, a time-series cleaned, anomaly-free, missing, dimensionality-reduced, and carbon-energy-correlation-matched full life-cycle carbon-energy coupled fusion dataset for highways is obtained.

[0026] According to an embodiment of the present invention, the step of constructing a dynamic highway lifecycle carbon footprint knowledge graph based on the highway lifecycle carbon-energy coupling fusion dataset and then deconstructing and splitting it to obtain a hierarchical highway lifecycle carbon footprint standard dataset specifically involves: Based on the node and edge relationships of the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a knowledge graph of highway lifecycle carbon footprint is constructed. The knowledge graph of the carbon footprint of the entire life cycle of the expressway is corrected by a preset algorithm model to obtain a dynamic knowledge graph of the carbon footprint of the entire life cycle of the expressway. Based on the dynamic highway lifecycle carbon footprint knowledge graph, the data is deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset.

[0027] This study involves in-depth mining of the carbon-energy coupling and fusion dataset across the entire lifecycle of highways. A five-element coupling relationship network is constructed, encompassing processes, materials, equipment, road sections, and time periods. Using these five core elements as knowledge graph entity nodes and edge relationships based on carbon emission transmission, consumption correlation, temporal matching, and spatial correlation among elements, a knowledge graph of the highway's entire lifecycle carbon footprint is built. This graph monitors real-time data on road service life, pavement deterioration index, equipment aging coefficient, and traffic flow change rate. Pre-defined algorithm models, such as a time-series weighted update algorithm, dynamically adjust the carbon emission contribution, correlation strength, and carbon loss coefficient of each node in the knowledge graph, enabling the carbon graph structure and weights to adaptively evolve with the actual road operating conditions. Instead of maintaining a fixed, static carbon ledger structure, a dynamic knowledge graph of the entire lifecycle carbon footprint of highways is obtained. This graph is then deconstructed across stages to identify carbon links. Carbon emissions throughout the entire lifecycle are deconstructed layer by layer according to the carbon links of building materials, construction process, operation and maintenance energy consumption, transportation, and decommissioning solid waste. Each data link is independently categorized into the time-series characteristics, energy consumption parameters, material consumption, and operating status data of the corresponding link. Direct carbon emission data, implicit carbon emission data, and indirect carbon loss data throughout the entire lifecycle are also separated. Through multi-dimensional, two-layer deconstruction, a refined classification of carbon emission sources, attributes, and links is achieved, resulting in a hierarchical standard dataset of the entire lifecycle carbon footprint of highways.

[0028] According to an embodiment of the present invention, the step of constructing a time-series prediction model based on the hierarchical highway full life-cycle carbon footprint standard dataset, obtaining a carbon energy time-series prediction dataset and comparing it to obtain a multi-dimensional anomaly tracing and identification result set specifically includes: Multi-dimensional impact features were extracted based on the hierarchical highway full life cycle carbon footprint standard dataset. The multi-dimensional influencing characteristics include road service life, pavement deterioration and damage level, traffic flow temporal fluctuation characteristics of road sections, seasonal climate conditions, and fluctuation coefficient of new energy power output in the road area. The multidimensional feature matrix is ​​obtained by processing the dimensional influence features in conjunction with the hierarchical highway full life cycle carbon footprint standard dataset. A time-series prediction model is constructed based on the multidimensional feature matrix to obtain a carbon energy time-series prediction dataset. An anomaly identification result set is obtained by comparing the carbon energy time series prediction dataset. Based on the anomaly identification result set, the location is determined to obtain a multidimensional anomaly tracing and identification result set.

[0029] This study extracts multi-dimensional impact features from the hierarchical highway full life cycle carbon footprint standard dataset. These features include road service life, pavement deterioration and damage levels, traffic flow temporal fluctuations, seasonal climate conditions, and fluctuation coefficients of renewable energy output in the road area. Range standardization and normalization are applied to these multi-dimensional impact features and carbon footprint temporal features to eliminate differences in dimensions and numerical magnitudes. Timestamp alignment is performed according to a unified temporal granularity to obtain a multi-dimensional feature matrix. Using this multi-dimensional feature matrix, historical carbon emission time-series data, and historical energy supply and demand time-series data as joint inputs, a long-term temporal dependency is mined using an LSTM layer. An attention mechanism adaptively allocates the weight contribution of each impact feature, strengthening the dominant role of key impact features in the prediction results. Training, validation, and test sets are defined, and a sliding window rolling training method is used to fit the full life cycle carbon emission time-series curve and energy supply and demand output curve. After model convergence, rolling predictions are performed according to short, medium, and long cycles to obtain carbon energy time-series prediction datasets for each road segment, time period, and life cycle stage, including predicted carbon emissions and energy load. The system extracts real-time measured carbon energy data and model-output carbon energy prediction data from the power supply and demand forecasts of wind, solar, and energy storage. It calculates the residuals between measured and predicted values ​​for each time-series sampling point, and uses a sliding window to statistically analyze the mean and standard deviation of the residuals within the window. An adaptive dynamic threshold interval is then constructed. By comparing the residuals with the dynamic threshold, anomalies such as excessive carbon emissions, energy supply and demand imbalances, and sensor-transmitted data distortion are identified. Anomaly points are marked with timestamps, road segment numbers, and anomaly type labels to obtain an anomaly identification result set. The dynamic threshold is then loaded. The knowledge graph of the carbon footprint of the entire life cycle of the expressway uses the road segment nodes and time period nodes corresponding to the marked abnormal time sequence points as the source tracing anchor points. It initiates the reverse topological traversal and positioning of the knowledge graph, and traces back the associated nodes of operating equipment, consumed materials, and carbon emission sources along the associated edges. It matches the equipment operating parameters, material consumption records and process condition information, and locks in the road segment, time period, equipment type, material category and carbon emission generation link of the abnormality level by level. It removes irrelevant topological branches and records the abnormal path and root cause information in a structured way to obtain a multi-dimensional abnormal source tracing and identification result set.

[0030] According to an embodiment of the present invention, the step of constructing a zero-carbon high-speed multi-objective collaborative optimization scheduling model based on the carbon energy time-series prediction dataset and the multi-dimensional anomaly tracing and identification result set, and solving it to obtain the globally optimal scheduling strategy and intelligent decision-making scheme, specifically includes: Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed. The zero-carbon high-speed multi-objective cooperative optimization scheduling model is solved by a preset algorithm to obtain the globally optimal scheduling strategy; The global optimal scheduling strategy includes a new energy regulation strategy, a load optimization allocation strategy, and a road network low-carbon management strategy. The intelligent decision-making scheme is obtained by processing the multidimensional anomaly tracing and identification result set. The intelligent decision-making schemes include intelligent road maintenance decision-making schemes, road area carbon sink optimization decision-making schemes, and low-carbon disposal decision-making schemes for decommissioned solid waste.

[0031] This involves extracting short-, medium-, and long-term time-of-use carbon emission forecasts, grid load forecasts, photovoltaic and wind power output forecasts, and energy storage charging and discharging potential time-of-use data from the carbon energy time-series prediction dataset. It also extracts located high-energy-consuming equipment sites, carbon emission exceeding standards road sections, abnormal road surface defects, insufficient carbon sink areas, inefficient solid waste disposal nodes, corresponding time periods, and causal labels from the multi-dimensional anomaly tracing and identification results. Pre-set optimization boundary constraints, including upper limits for new energy output, energy storage capacity constraints, road network traffic flow control thresholds, road maintenance period constraints, carbon sink expansion area constraints, and solid waste disposal emission standard constraints, constructs a zero-carbon highway multi-objective collaborative optimization scheduling model, and establishes three major... The optimization objectives are to minimize total carbon emissions across the entire road segment and all time periods, maximize the local utilization rate of wind and solar renewable energy in the road area, and minimize the comprehensive operating costs of highway maintenance electricity and equipment operation energy consumption. Anomaly tracing results are embedded as rigid constraints. For high-carbon emission, high-energy-consumption, and defect anomaly points located through tracing, priority control weights and mandatory rectification constraints are set to prevent optimization results from deviating from actual on-site problems. A Pareto optimal solution is obtained for the multi-objective model using preset algorithms such as intelligent optimization algorithms, yielding a globally optimal scheduling strategy, including renewable energy control strategies, load optimization allocation strategies, and low-carbon management strategies for the road network. Based on the anomaly tracing results of road surface deterioration, the system automatically matches the defect level, road segment location, and most... During optimal maintenance windows, intelligent road maintenance decision-making schemes are generated, including low-carbon maintenance process selection, staggered scheduling of maintenance operations, and low-carbon machinery configuration. This reduces carbon emissions associated with maintenance construction. Based on carbon sequestration prediction gaps and areas with abnormal vegetation, road area carbon sequestration optimization decision-making schemes are generated, including optimal selection of carbon sequestration vegetation replanting types, replanting location planning, and phased maintenance irrigation timing. This enhances the road area's natural carbon sequestration offsetting capacity. For nodes with high energy consumption and abnormal carbon emissions in solid waste disposal, automatic decision-making schemes for low-carbon disposal of decommissioned solid waste are generated, including the recycling ratio of waste road materials, low-carbon planning of transportation routes, and staggered operation of disposal plants. This reduces the overall carbon consumption in the decommissioning and dismantling process, integrating globally optimal scheduling strategies and... The intelligent decision-making scheme is issued to the business system for execution. During the execution process, new operating condition time-series data, actual energy consumption data, actual carbon emission data, road surface condition update data, actual output data of new energy sources, and solid waste disposal operation data are collected. The newly added full-cycle data is standardized and organized according to the spatiotemporal anchoring rules of mileage marker + timestamp in step one. The data is then returned and incorporated into the full-cycle multi-source original dataset of step one, and enters the next round of progressive processing flow of "classification - cleaning - map construction - prediction and early warning - optimization decision". This enables the strategy to continuously adapt and iterate with the road network status, traffic flow, climate, and facility aging, forming a closed-loop iterative full-cycle intelligent data management process for zero-carbon highways.

[0032] Please refer to Figure 3 , Figure 3 This is a high-level flowchart of a zero-carbon highway full-lifecycle intelligent management method according to some embodiments of this application.

[0033] This invention also discloses a zero-carbon highway full-lifecycle intelligent management system, including a memory and a processor. The memory includes a zero-carbon highway full-lifecycle intelligent management method program. When the processor executes the zero-carbon highway full-lifecycle intelligent management method program, it performs the following steps: Obtain heterogeneous multi-source time-series data of highways and perform preprocessing to obtain a standardized spatiotemporal raw dataset of highways throughout their entire lifecycle. The original spatiotemporally standardized dataset of the entire life cycle of the expressway is processed to obtain a high-quality time-series dataset of the entire life cycle of the expressway, which is then fused to obtain a carbon-energy coupling fusion dataset of the entire life cycle of the expressway. Based on the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a dynamic highway lifecycle carbon footprint knowledge graph is constructed and deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset. Based on the hierarchical highway full life cycle carbon footprint standard dataset, a time series prediction model is constructed to obtain a carbon energy time series prediction dataset and compare it to obtain a multi-dimensional anomaly tracing and identification result set. Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed and solved to obtain the globally optimal scheduling strategy and intelligent decision-making scheme.

[0034] This process involves acquiring and preprocessing heterogeneous multi-source time-series data of highways to obtain a standardized spatiotemporal dataset of the entire highway lifecycle. This standardized dataset is then processed to obtain a high-quality time-series dataset of the entire highway lifecycle, which is then fused to obtain a carbon-energy coupled fusion dataset of the entire highway lifecycle. Based on this dataset, a dynamic knowledge graph of the carbon footprint of the entire highway lifecycle is constructed, deconstructed, and split to obtain a hierarchical standard dataset of the carbon footprint of the entire highway lifecycle. Finally, a time-series prediction model is built based on this standard dataset, resulting in a carbon energy time-series prediction dataset, which is then compared to obtain multiple... The system utilizes a multi-dimensional anomaly source identification result set to construct and solve a zero-carbon highway multi-objective collaborative optimization scheduling model based on the carbon energy time series prediction dataset and the multi-dimensional anomaly source identification result set. This yields the globally optimal scheduling strategy and intelligent decision-making scheme. Through the full-domain acquisition of heterogeneous multi-source raw time series data throughout the entire life cycle and unified anchoring of the time series benchmark, deep cleaning and carbon energy coupling fusion of multi-dimensional data based on time series difference, construction and hierarchical deconstruction of dynamic carbon footprint knowledge graph, intelligent prediction of carbon energy time series throughout the entire life cycle and multi-dimensional anomaly source identification, and closed-loop iteration of multi-objective optimization scheduling and intelligent decision-making throughout the entire life cycle of the zero-carbon highway, the system achieves intelligent processing of data throughout the entire life cycle of the zero-carbon highway, refined carbon footprint accounting, anomaly source tracing, and low-carbon optimization decision-making.

[0035] According to an embodiment of the present invention, the step of acquiring heterogeneous multi-source time-series data of highways and performing preprocessing to obtain a spatiotemporally standardized raw dataset of the entire highway lifecycle specifically involves: Acquire heterogeneous multi-source time-series data of highways, including planning and design parameter data, building material production and transportation ledger data, construction energy consumption and emission monitoring data, roadside new energy power generation and supply data, road network traffic flow perception data, tunnel electromechanical operation and maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling and resource utilization data. Time series processing is performed on the heterogeneous multi-source time series data of the expressway to obtain standard expressway time series multi-source data. Mapping the time-series multi-source data of the standard highway to obtain spatiotemporal multi-source data of the standard highway; The standard highway spatiotemporal multi-source data is preprocessed to obtain a standardized original dataset of the highway throughout its entire lifecycle.

[0036] This involves simultaneously acquiring heterogeneous multi-source time-series data from four stages of highway development—planning, construction, operation, and decommissioning—through a parallel acquisition method. This includes planning and design parameter data, building material production and transportation records, construction energy consumption and emission monitoring data, roadside renewable energy power generation data, road network traffic flow perception data, tunnel electromechanical maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling, and resource utilization data. All acquired heterogeneous multi-source time-series data is stamped with BeiDou UTC millisecond-level timestamps and road segment stationing spatial codes. Time-series resampling and alignment algorithms are used to eliminate time-series offsets caused by different terminals, sampling frequencies, and transmission delays, resulting in standard highway time-series multi-source data. This achieves precise alignment of data across the entire lifecycle on a unified timeline. Furthermore, a multi-source data spatial mapping method is used to integrate BIM 3D model data, IoT sensor time-series data, and other data. Human-machine inspection point cloud data, vehicle-mounted perception data, and maintenance ledger text data are uniformly mapped to the same spatiotemporal coordinate system through coordinate transformation and spatial matching algorithms. This yields standardized spatiotemporal multi-source data of highways that are uniquely correlated in spatial dimension, can be located, and can be retrieved. Carbon feature standardization coding methods are used to encode carbon features of carbon data sources, completing identification, classification, and calculable processing. Format normalization and desensitization encryption methods are used to unify fields, normalize units, and standardize dimensions of multi-source heterogeneous data. Sensitive data and key engineering information are hash-desensitized and symmetrically encrypted to complete data security processing. This results in a standardized spatiotemporal raw dataset of highways that is unified in spatiotemporal reference, standardized in format, correlateable, traceable, and calculable. This addresses the systemic defects of existing technologies, such as spatiotemporal misalignment of data across stages, stage fragmentation, inability to connect, and difficulty in full life-cycle carbon traceability, from the bottom layer of data processing.

[0037] According to an embodiment of the present invention, the step of processing the original spatiotemporally standardized dataset of the entire highway lifecycle to obtain a high-quality time-series dataset of the entire highway lifecycle and then fusing it to obtain a carbon-energy coupled fused dataset of the entire highway lifecycle specifically involves: Outlier removal is performed on the original spatiotemporally standardized dataset of the entire life cycle of the expressway to obtain a clean time-series dataset of the entire life cycle of the expressway. Denoising and dimensionality reduction are performed on the clean highway full life cycle time series dataset to obtain a low-dimensional highway full life cycle time series feature dataset. Time series completion is performed based on the low-dimensional highway full life cycle time series feature dataset to obtain a high-quality highway full life cycle time series dataset. By fusing the high-quality highway lifecycle time-series dataset, a highway lifecycle carbon-energy coupled fusion dataset is obtained.

[0038] Specifically, the entire lifecycle time-series dataset of highways was identified and anomalous jump points caused by sensor drift, network jitter, and equipment malfunctions were removed using first-order temporal difference and the 3σ criterion. After removing anomalous points, the dataset was rearranged according to the original timestamps to obtain a clean, anomalous highway lifecycle time-series dataset. Wavelet threshold denoising and principal component analysis were then used to process this clean dataset for dimensionality reduction, resulting in a low-dimensional, redundant highway lifecycle time-series feature dataset. Neighborhood correlation interpolation was then used to fill in the time-series breakpoints in the low-dimensional highway lifecycle time-series feature dataset, resulting in a high-quality highway lifecycle time-series dataset. This process achieved denoising, purification, and dimensionality reduction of high-dimensional carbon-related data. Based on this high-quality highway lifecycle time-series dataset, further... Energy consumption and carbon emissions are defined as follows: energy consumption includes photovoltaic power output, wind power output, equipment power consumption, fuel consumption, and transportation energy consumption; carbon emissions include carbon emissions from direct combustion, indirect carbon emissions from electricity use, carbon emissions from building materials, and carbon absorption by carbon sinks. A mapping table is established, linking various energy sources to their corresponding benchmark carbon emission characteristics. The cleaned energy consumption time-series data and carbon emission monitoring data are unified to the same time-series sampling granularity. Field association is performed by timestamp, road segment number, and time segment label. Energy consumption characteristics, carbon emission characteristics, road surface condition characteristics, and traffic flow characteristics are spliced ​​together to construct a fusion data table with a unified field structure and a unified spatiotemporal index. Finally, a time-series cleaned, anomaly-free, missing, dimensionality-reduced, and carbon-energy-correlation-matched full life-cycle carbon-energy coupled fusion dataset for highways is obtained.

[0039] According to an embodiment of the present invention, the step of constructing a dynamic highway lifecycle carbon footprint knowledge graph based on the highway lifecycle carbon-energy coupling fusion dataset and then deconstructing and splitting it to obtain a hierarchical highway lifecycle carbon footprint standard dataset specifically involves: Based on the node and edge relationships of the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a knowledge graph of highway lifecycle carbon footprint is constructed. The knowledge graph of the carbon footprint of the entire life cycle of the expressway is corrected by a preset algorithm model to obtain a dynamic knowledge graph of the carbon footprint of the entire life cycle of the expressway. Based on the dynamic highway lifecycle carbon footprint knowledge graph, the data is deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset.

[0040] This study involves in-depth mining of the carbon-energy coupling and fusion dataset across the entire lifecycle of highways. A five-element coupling relationship network is constructed, encompassing processes, materials, equipment, road sections, and time periods. Using these five core elements as knowledge graph entity nodes and edge relationships based on carbon emission transmission, consumption correlation, temporal matching, and spatial correlation among elements, a knowledge graph of the highway's entire lifecycle carbon footprint is built. This graph monitors real-time data on road service life, pavement deterioration index, equipment aging coefficient, and traffic flow change rate. Pre-defined algorithm models, such as a time-series weighted update algorithm, dynamically adjust the carbon emission contribution, correlation strength, and carbon loss coefficient of each node in the knowledge graph, enabling the carbon graph structure and weights to adaptively evolve with the actual road operating conditions. Instead of maintaining a fixed, static carbon ledger structure, a dynamic knowledge graph of the entire lifecycle carbon footprint of highways is obtained. This graph is then deconstructed across stages to identify carbon links. Carbon emissions throughout the entire lifecycle are deconstructed layer by layer according to the carbon links of building materials, construction process, operation and maintenance energy consumption, transportation, and decommissioning solid waste. Each data link is independently categorized into the time-series characteristics, energy consumption parameters, material consumption, and operating status data of the corresponding link. Direct carbon emission data, implicit carbon emission data, and indirect carbon loss data throughout the entire lifecycle are also separated. Through multi-dimensional, two-layer deconstruction, a refined classification of carbon emission sources, attributes, and links is achieved, resulting in a hierarchical standard dataset of the entire lifecycle carbon footprint of highways.

[0041] According to an embodiment of the present invention, the step of constructing a time-series prediction model based on the hierarchical highway full life-cycle carbon footprint standard dataset, obtaining a carbon energy time-series prediction dataset and comparing it to obtain a multi-dimensional anomaly tracing and identification result set specifically includes: Multi-dimensional impact features were extracted based on the hierarchical highway full life cycle carbon footprint standard dataset. The multi-dimensional influencing characteristics include road service life, pavement deterioration and damage level, traffic flow temporal fluctuation characteristics of road sections, seasonal climate conditions, and fluctuation coefficient of new energy power output in the road area. The multidimensional feature matrix is ​​obtained by processing the dimensional influence features in conjunction with the hierarchical highway full life cycle carbon footprint standard dataset. A time-series prediction model is constructed based on the multidimensional feature matrix to obtain a carbon energy time-series prediction dataset. An anomaly identification result set is obtained by comparing the carbon energy time series prediction dataset. Based on the anomaly identification result set, the location is determined to obtain a multidimensional anomaly tracing and identification result set.

[0042] This study extracts multi-dimensional impact features from the hierarchical highway full life cycle carbon footprint standard dataset. These features include road service life, pavement deterioration and damage levels, traffic flow temporal fluctuations, seasonal climate conditions, and fluctuation coefficients of renewable energy output in the road area. Range standardization and normalization are applied to these multi-dimensional impact features and carbon footprint temporal features to eliminate differences in dimensions and numerical magnitudes. Timestamp alignment is performed according to a unified temporal granularity to obtain a multi-dimensional feature matrix. Using this multi-dimensional feature matrix, historical carbon emission time-series data, and historical energy supply and demand time-series data as joint inputs, a long-term temporal dependency is mined using an LSTM layer. An attention mechanism adaptively allocates the weight contribution of each impact feature, strengthening the dominant role of key impact features in the prediction results. Training, validation, and test sets are defined, and a sliding window rolling training method is used to fit the full life cycle carbon emission time-series curve and energy supply and demand output curve. After model convergence, rolling predictions are performed according to short, medium, and long cycles to obtain carbon energy time-series prediction datasets for each road segment, time period, and life cycle stage, including predicted carbon emissions and energy load. The system extracts real-time measured carbon energy data and model-output carbon energy prediction data from the power supply and demand forecasts of wind, solar, and energy storage. It calculates the residuals between measured and predicted values ​​for each time-series sampling point, and uses a sliding window to statistically analyze the mean and standard deviation of the residuals within the window. An adaptive dynamic threshold interval is then constructed. By comparing the residuals with the dynamic threshold, anomalies such as excessive carbon emissions, energy supply and demand imbalances, and sensor-transmitted data distortion are identified. Anomaly points are marked with timestamps, road segment numbers, and anomaly type labels to obtain an anomaly identification result set. The dynamic threshold is then loaded. The knowledge graph of the carbon footprint of the entire life cycle of the expressway uses the road segment nodes and time period nodes corresponding to the marked abnormal time sequence points as the source tracing anchor points. It initiates the reverse topological traversal and positioning of the knowledge graph, and traces back the associated nodes of operating equipment, consumed materials, and carbon emission sources along the associated edges. It matches the equipment operating parameters, material consumption records and process condition information, and locks in the road segment, time period, equipment type, material category and carbon emission generation link of the abnormality level by level. It removes irrelevant topological branches and records the abnormal path and root cause information in a structured way to obtain a multi-dimensional abnormal source tracing and identification result set.

[0043] According to an embodiment of the present invention, the step of constructing a zero-carbon high-speed multi-objective collaborative optimization scheduling model based on the carbon energy time-series prediction dataset and the multi-dimensional anomaly tracing and identification result set, and solving it to obtain the globally optimal scheduling strategy and intelligent decision-making scheme, specifically includes: Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed. The zero-carbon high-speed multi-objective cooperative optimization scheduling model is solved by a preset algorithm to obtain the globally optimal scheduling strategy; The global optimal scheduling strategy includes a new energy regulation strategy, a load optimization allocation strategy, and a road network low-carbon management strategy. The intelligent decision-making scheme is obtained by processing the multidimensional anomaly tracing and identification result set. The intelligent decision-making schemes include intelligent road maintenance decision-making schemes, road area carbon sink optimization decision-making schemes, and low-carbon disposal decision-making schemes for decommissioned solid waste.

[0044] This involves extracting short-, medium-, and long-term time-of-use carbon emission forecasts, grid load forecasts, photovoltaic and wind power output forecasts, and energy storage charging and discharging potential time-of-use data from the carbon energy time-series prediction dataset. It also extracts located high-energy-consuming equipment sites, carbon emission exceeding standards road sections, abnormal road surface defects, insufficient carbon sink areas, inefficient solid waste disposal nodes, corresponding time periods, and causal labels from the multi-dimensional anomaly tracing and identification results. Pre-set optimization boundary constraints, including upper limits for new energy output, energy storage capacity constraints, road network traffic flow control thresholds, road maintenance period constraints, carbon sink expansion area constraints, and solid waste disposal emission standard constraints, constructs a zero-carbon highway multi-objective collaborative optimization scheduling model, and establishes three major... The optimization objectives are to minimize total carbon emissions across the entire road segment and all time periods, maximize the local utilization rate of wind and solar renewable energy in the road area, and minimize the comprehensive operating costs of highway maintenance electricity and equipment operation energy consumption. Anomaly tracing results are embedded as rigid constraints. For high-carbon emission, high-energy-consumption, and defect anomaly points located through tracing, priority control weights and mandatory rectification constraints are set to prevent optimization results from deviating from actual on-site problems. A Pareto optimal solution is obtained for the multi-objective model using preset algorithms such as intelligent optimization algorithms, yielding a globally optimal scheduling strategy, including renewable energy control strategies, load optimization allocation strategies, and low-carbon management strategies for the road network. Based on the anomaly tracing results of road surface deterioration, the system automatically matches the defect level, road segment location, and most... During optimal maintenance windows, intelligent road maintenance decision-making schemes are generated, including low-carbon maintenance process selection, staggered scheduling of maintenance operations, and low-carbon machinery configuration. This reduces carbon emissions associated with maintenance construction. Based on carbon sequestration prediction gaps and areas with abnormal vegetation, road area carbon sequestration optimization decision-making schemes are generated, including optimal selection of carbon sequestration vegetation replanting types, replanting location planning, and phased maintenance irrigation timing. This enhances the road area's natural carbon sequestration offsetting capacity. For nodes with high energy consumption and abnormal carbon emissions in solid waste disposal, automatic decision-making schemes for low-carbon disposal of decommissioned solid waste are generated, including the recycling ratio of waste road materials, low-carbon planning of transportation routes, and staggered operation of disposal plants. This reduces the overall carbon consumption in the decommissioning and dismantling process, integrating globally optimal scheduling strategies and... The intelligent decision-making scheme is issued to the business system for execution. During the execution process, new operating condition time-series data, actual energy consumption data, actual carbon emission data, road surface condition update data, actual output data of new energy sources, and solid waste disposal operation data are collected. The newly added full-cycle data is standardized and organized according to the spatiotemporal anchoring rules of mileage marker + timestamp in step one. The data is then returned and incorporated into the full-cycle multi-source original dataset of step one, and enters the next round of progressive processing flow of "classification - cleaning - map construction - prediction and early warning - optimization decision". This enables the strategy to continuously adapt and iterate with the road network status, traffic flow, climate, and facility aging, forming a closed-loop iterative full-cycle intelligent data management process for zero-carbon highways.

[0045] A third aspect of the present invention provides a readable storage medium comprising a program for a zero-carbon highway full-cycle intelligent management method, wherein when the program is executed by a processor, it implements the steps of the zero-carbon highway full-cycle intelligent management method as described in any of the preceding claims.

[0046] This invention discloses a zero-carbon highway full-lifecycle intelligent management method, system, and medium. It acquires heterogeneous multi-source time-series data of highways and preprocesses it to obtain a standardized spatiotemporal raw dataset for the entire highway lifecycle. This standardized raw dataset is then processed to obtain a high-quality highway full-lifecycle time-series dataset, which is then fused to obtain a highway full-lifecycle carbon-energy coupled fused dataset. A dynamic highway full-lifecycle carbon footprint knowledge graph is constructed based on this dataset and deconstructed and split to obtain a hierarchical highway full-lifecycle carbon footprint standard dataset. Finally, a time-series prediction model is constructed based on this hierarchical highway full-lifecycle carbon footprint standard dataset to obtain carbon-energy time-series data. The system compares and contrasts time-series prediction datasets to obtain a multi-dimensional anomaly tracing and identification result set. Based on the carbon energy time-series prediction dataset and the multi-dimensional anomaly tracing and identification result set, a zero-carbon highway multi-objective collaborative optimization scheduling model is constructed and solved to obtain the globally optimal scheduling strategy and intelligent decision-making scheme. Through the full-domain acquisition of heterogeneous multi-source raw time-series data throughout the entire life cycle and unified anchoring of time-series benchmarks, deep cleaning of multi-dimensional data based on time-series differences and carbon energy coupling and fusion, construction and hierarchical deconstruction of dynamic carbon footprint knowledge graph, intelligent prediction of carbon energy time-series data throughout the entire life cycle and multi-dimensional anomaly tracing and identification, and closed-loop iteration of zero-carbon highway multi-objective optimization scheduling and full-cycle intelligent decision-making, the system realizes intelligent processing of zero-carbon highway full-life-cycle data, refined carbon footprint accounting, anomaly tracing, and low-carbon optimization decision-making.

[0047] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0048] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0049] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0050] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0051] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for intelligent management of zero-carbon highways throughout their entire lifecycle, characterized in that, Includes the following steps: Obtain heterogeneous multi-source time-series data of highways and perform preprocessing to obtain a standardized spatiotemporal raw dataset of highways throughout their entire lifecycle. The original spatiotemporally standardized dataset of the entire life cycle of the expressway is processed to obtain a high-quality time-series dataset of the entire life cycle of the expressway, which is then fused to obtain a carbon-energy coupling fusion dataset of the entire life cycle of the expressway. Based on the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a dynamic highway lifecycle carbon footprint knowledge graph is constructed and deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset. Based on the hierarchical highway full life cycle carbon footprint standard dataset, a time series prediction model is constructed to obtain a carbon energy time series prediction dataset and compare it to obtain a multi-dimensional anomaly tracing and identification result set. Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed and solved to obtain the globally optimal scheduling strategy and intelligent decision-making scheme.

2. The intelligent management method for the entire lifecycle of zero-carbon highways according to claim 1, characterized in that, The process of acquiring heterogeneous multi-source time-series data of highways and performing preprocessing to obtain a standardized spatiotemporal raw dataset of highways throughout their entire lifecycle includes: Acquire heterogeneous multi-source time-series data of highways, including planning and design parameter data, building material production and transportation ledger data, construction energy consumption and emission monitoring data, roadside new energy power generation and supply data, road network traffic flow perception data, tunnel electromechanical operation and maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling and resource utilization data. Time series processing is performed on the heterogeneous multi-source time series data of the expressway to obtain standard expressway time series multi-source data. Mapping the time-series multi-source data of the standard highway to obtain spatiotemporal multi-source data of the standard highway; The standard highway spatiotemporal multi-source data is preprocessed to obtain a standardized original dataset of the highway throughout its entire lifecycle.

3. The intelligent management method for the entire lifecycle of zero-carbon highways according to claim 2, characterized in that, The process involves processing the original spatiotemporally standardized dataset of the entire highway lifecycle to obtain a high-quality time-series dataset of the entire highway lifecycle, which is then fused to obtain a carbon-energy coupled fused dataset of the entire highway lifecycle, including: Outlier removal is performed on the original spatiotemporally standardized dataset of the entire life cycle of the expressway to obtain a clean time-series dataset of the entire life cycle of the expressway. Denoising and dimensionality reduction are performed on the clean highway full life cycle time series dataset to obtain a low-dimensional highway full life cycle time series feature dataset. Time series completion is performed based on the low-dimensional highway full life cycle time series feature dataset to obtain a high-quality highway full life cycle time series dataset. By fusing the high-quality highway lifecycle time-series dataset, a highway lifecycle carbon-energy coupled fusion dataset is obtained.

4. The intelligent management method for the entire lifecycle of zero-carbon highways according to claim 1, characterized in that, The process involves constructing a dynamic highway lifecycle carbon footprint knowledge graph based on the highway lifecycle carbon-energy coupling and fusion dataset, and then deconstructing and splitting it to obtain a hierarchical highway lifecycle carbon footprint standard dataset, including: Based on the node and edge relationships of the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a knowledge graph of highway lifecycle carbon footprint is constructed. The knowledge graph of the carbon footprint of the entire life cycle of the expressway is corrected by a preset algorithm model to obtain a dynamic knowledge graph of the carbon footprint of the entire life cycle of the expressway. Based on the dynamic highway lifecycle carbon footprint knowledge graph, the data is deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset.

5. The intelligent management method for the entire lifecycle of zero-carbon highways according to claim 1, characterized in that, The step involves constructing a time-series prediction model based on the hierarchical highway life-cycle carbon footprint standard dataset, obtaining a carbon energy time-series prediction dataset, comparing it, and obtaining a multi-dimensional anomaly tracing and identification result set, including: Multi-dimensional impact features were extracted based on the hierarchical highway full life cycle carbon footprint standard dataset. The multi-dimensional influencing characteristics include road service life, pavement deterioration and damage level, traffic flow temporal fluctuation characteristics of road sections, seasonal climate conditions, and fluctuation coefficient of new energy power output in the road area. The multidimensional feature matrix is ​​obtained by processing the dimensional influence features in conjunction with the hierarchical highway full life cycle carbon footprint standard dataset. A time-series prediction model is constructed based on the multidimensional feature matrix to obtain a carbon energy time-series prediction dataset. An anomaly identification result set is obtained by comparing the carbon energy time series prediction dataset. Based on the anomaly identification result set, the location is determined to obtain a multidimensional anomaly tracing and identification result set.

6. The intelligent management method for the entire lifecycle of zero-carbon highways according to claim 1, characterized in that, The step of constructing and solving a zero-carbon high-speed multi-objective collaborative optimization scheduling model based on the carbon energy time-series prediction dataset and the multi-dimensional anomaly source identification result set to obtain the globally optimal scheduling strategy and intelligent decision-making scheme includes: Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed. The zero-carbon high-speed multi-objective cooperative optimization scheduling model is solved by a preset algorithm to obtain the globally optimal scheduling strategy; The global optimal scheduling strategy includes a new energy regulation strategy, a load optimization allocation strategy, and a road network low-carbon management strategy. The intelligent decision-making scheme is obtained by processing the multidimensional anomaly tracing and identification result set. The intelligent decision-making schemes include intelligent road maintenance decision-making schemes, road area carbon sink optimization decision-making schemes, and low-carbon disposal decision-making schemes for decommissioned solid waste.

7. A zero-carbon highway full-lifecycle intelligent management system, characterized in that, The system includes a memory and a processor. The memory contains a program for a zero-carbon highway full-lifecycle intelligent management method. When the program for the zero-carbon highway full-lifecycle intelligent management method is executed by the processor, it performs the following steps: Obtain heterogeneous multi-source time-series data of highways and perform preprocessing to obtain a standardized spatiotemporal raw dataset of highways throughout their entire lifecycle. The original spatiotemporally standardized dataset of the entire life cycle of the expressway is processed to obtain a high-quality time-series dataset of the entire life cycle of the expressway, which is then fused to obtain a carbon-energy coupling fusion dataset of the entire life cycle of the expressway. Based on the aforementioned highway lifecycle carbon energy coupling and fusion dataset, a dynamic highway lifecycle carbon footprint knowledge graph is constructed and deconstructed and split to obtain a hierarchical highway lifecycle carbon footprint standard dataset. Based on the hierarchical highway full life cycle carbon footprint standard dataset, a time series prediction model is constructed to obtain a carbon energy time series prediction dataset and compare it to obtain a multi-dimensional anomaly tracing and identification result set. Based on the carbon energy time series prediction dataset and the multidimensional anomaly tracing and identification result set, a zero-carbon high-speed multi-objective collaborative optimization scheduling model is constructed and solved to obtain the globally optimal scheduling strategy and intelligent decision-making scheme.

8. The zero-carbon highway full-lifecycle intelligent management system according to claim 7, characterized in that, The process of acquiring heterogeneous multi-source time-series data of highways and performing preprocessing to obtain a standardized spatiotemporal raw dataset of highways throughout their entire lifecycle includes: Acquire heterogeneous multi-source time-series data of highways, including planning and design parameter data, building material production and transportation ledger data, construction energy consumption and emission monitoring data, roadside new energy power generation and supply data, road network traffic flow perception data, tunnel electromechanical operation and maintenance data, pavement structure deterioration monitoring data, and decommissioning, dismantling and resource utilization data. Time series processing is performed on the heterogeneous multi-source time series data of the expressway to obtain standard expressway time series multi-source data. Mapping the time-series multi-source data of the standard highway to obtain spatiotemporal multi-source data of the standard highway; The standard highway spatiotemporal multi-source data is preprocessed to obtain a standardized original dataset of the highway throughout its entire lifecycle.

9. The zero-carbon highway full-lifecycle intelligent management system according to claim 8, characterized in that, The process involves processing the original spatiotemporally standardized dataset of the entire highway lifecycle to obtain a high-quality time-series dataset of the entire highway lifecycle, which is then fused to obtain a carbon-energy coupled fused dataset of the entire highway lifecycle, including: Outlier removal is performed on the original spatiotemporally standardized dataset of the entire life cycle of the expressway to obtain a clean time-series dataset of the entire life cycle of the expressway. Denoising and dimensionality reduction are performed on the clean highway full life cycle time series dataset to obtain a low-dimensional highway full life cycle time series feature dataset. Time series completion is performed based on the low-dimensional highway full life cycle time series feature dataset to obtain a high-quality highway full life cycle time series dataset. By fusing the high-quality highway lifecycle time-series dataset, a highway lifecycle carbon-energy coupled fusion dataset is obtained.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a program for a zero-carbon highway full-lifecycle intelligent management method. When the program is executed by a processor, it implements the steps of the zero-carbon highway full-lifecycle intelligent management method as described in any one of claims 1 to 6.

Images