Source point identification and control method for carbon emission of ultra-high voltage engineering design and construction

Abstract

The application discloses a method for identifying and controlling carbon emission sources in extra-high voltage engineering design and construction, which comprises the following steps: collecting multi-dimensional carbon emission related parameters in the whole process of design and construction, extracting carbon emission source characteristics and dividing data subsets through panoramic mapping model, realizing preliminary positioning of carbon emission sources by using time-space coupling dynamic identification technology, screening effective data and classifying source types by means of abnormal detection clustering algorithm, simulating carbon emission changes under different control strategies through dynamic simulation deduction, and finally generating a targeted control scheme. The method is implemented in multiple steps and stages, integrates the advantages of collaborative application of multiple models, solves the problems of fuzzy source positioning and lack of targeted control scheme in traditional technology, realizes comprehensive identification, accurate positioning and efficient control of carbon emission sources in extra-high voltage engineering design and construction, and improves the fine level and implementation efficiency of carbon emission control.

Description

Technical Field

[0001] This invention relates to the field of carbon emission identification technology for ultra-high voltage (UHV) projects, and particularly to a method for identifying and controlling carbon emission sources during the design and construction of UHV projects. Background Technology

[0002] As ultra-high-voltage (UHV) power transmission projects expand to large-scale, complex terrain areas, the design and construction processes involve the deployment of diverse equipment, the consumption of various materials, and the overlapping of multiple procedures. Carbon emission sources are characterized by wide distribution, diverse types, and dynamic changes. Guided by the "dual carbon" goals, the power industry has imposed rigid requirements on the full-process carbon emission control of UHV projects, necessitating precise tracking and efficient management of carbon emission sources from design planning to construction implementation. Currently, carbon emission-related work in UHV projects relies heavily on traditional monitoring methods and has not yet formed a systematic identification and control system covering the entire process and integrating multi-dimensional data. This system is ill-suited to the refined carbon emission management needs under complex engineering conditions, necessitating the development of targeted technical methods to fill this industry gap.

[0003] Existing technologies have significant shortcomings in the identification and control of carbon emission sources in ultra-high voltage (UHV) projects. On the one hand, the identification of carbon emission sources lacks in-depth spatiotemporal coupling analysis, relying solely on single-type data or local monitoring results. This fails to comprehensively capture the differences in carbon emission contributions across different construction stages, locations, and equipment types, leading to vague source location and inaccurate classification, making it difficult to support precise control decisions. On the other hand, the formulation of control strategies does not incorporate dynamic simulation and deduction technologies, failing to fully consider the dynamic changes in operating parameters and environmental conditions during project construction. The control schemes lack flexibility and specificity, and the absence of a data anomaly screening and effective classification mechanism makes them susceptible to interference from invalid data, resulting in poor implementation of control measures and an inability to achieve efficient control of carbon emission sources. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides a method for identifying and controlling carbon emission sources in the design and construction of ultra-high voltage power transmission projects.

[0005] The technical solution adopted in this invention is a method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage (UHV) power transmission projects, comprising the following steps: S1, collecting topographic parameters of the line laying area, equipment installation condition parameters, construction machinery operation parameters, material consumption parameters, energy consumption type parameters, and environmental impact parameters through a carbon emission monitoring terminal throughout the entire UHV power transmission project design and construction process, and constructing a multi-dimensional raw carbon emission data set; S2, extracting carbon emission source features from the raw data set based on an UHV carbon emission panoramic mapping model, establishing a mapping relationship between carbon emission data and source type, and dividing the carbon emission data subsets into design and construction phases; S3, using a spatiotemporally coupled carbon source dynamic identification model to analyze the divided data. The carbon emission data subset is decomposed into spatiotemporal dimensions to initially locate carbon emission sources for different construction procedures, equipment types, and regional locations; S4, anomaly detection and clustering algorithms are used to filter out outliers and perform clustering analysis on the initially located carbon emission sources, eliminating invalid data and classifying carbon emission sources of the same type; S5, a construction carbon emission dynamic simulation analysis platform is used to dynamically simulate and extrapolate the clustered carbon emission source data to simulate the carbon emission change trends under different control strategies; S6, based on the simulation results, combined with the carbon emission control threshold parameters of the UHV project and the source priority weight parameters, a targeted carbon emission source control plan is generated to complete the dynamic control of carbon emission sources.

[0006] Furthermore, the expression for the ultra-high voltage carbon emission panoramic mapping model is: ,in, This is the panoramic mapping coefficient for ultra-high voltage carbon emissions; For the i-th type of carbon emission source point weighting parameter; The carbon emission intensity parameter for the i-th type of source point; The duration parameter for the i-th type of source point; The terrain adaptation coefficient for the i-th type of source point; Let be the carbon emission coefficient of the i-th source material; The power weight of the j-th type of construction equipment; For the energy consumption parameters of the j-th type of construction equipment; Let J be the efficiency coefficient of the j-th type of construction procedure; is the correction factor for the design and construction phase; n is the total number of carbon emission source types; m is the total number of construction equipment types.

[0007] Furthermore, the expression for the spatiotemporally coupled carbon source dynamic identification model is: ,in, Spacetime coordinates The intensity of carbon source identification at the location; The spatial coupling coefficient; The time coupling coefficient; Let t be the carbon emission concentration parameter at time t; coordinates Distance attenuation coefficient at that location; This is a spatiotemporal coupling correction factor; For the k-th type of construction process, in coordinates Carbon emission contribution value at the location; is the sensitivity parameter for identifying the k-th type of carbon source point; p is the total number of construction procedures; t represents the spatial coordinate parameter; t represents the time parameter.

[0008] Furthermore, the expression for the carbon emission data anomaly detection clustering algorithm is as follows: ,in, For carbon emission data cluster center parameters; This represents the q-th carbon emission data sample value; Let q be the anomaly detection coefficient for the q-th data point; The weight of the q-th data density; Let r be the initial center of the r-th cluster; Let r be the distance parameter within the r-th cluster; Let be the similarity coefficient of the r-th cluster; Let t be the error value of the t-th data point; Let t be the error weight; This is the vth valid data value; is the correlation coefficient of the v-th data point; q is the total number of data samples; s is the number of clusters; u is the number of error data points; This represents the number of valid data points.

[0009] Furthermore, the carbon emission trend projection expression of the construction carbon emission dynamic simulation analysis platform is as follows: ,in, for Simulated carbon emissions values ​​at any given time; For the simulation adaptation coefficients of the mapping model; To identify the simulation weight coefficients of the model; These are the correction coefficients for the clustering algorithm simulation. These are the error parameters for the simulation system; For Category O control measures The execution intensity parameter at any given time; Total number of control measures types; This is the simulation time step; This is the time variable for integration.

[0010] Furthermore, the expression for the generation model of the carbon emission source control scheme for the design and construction of the ultra-high voltage project is as follows: ,in, Parameters for carbon emission source control strategies; This is the source point priority coefficient; The intensity of implementation of the h-th type of control strategy; The technical efficiency parameter for the h-th type of control strategy; This represents the total number of control strategy types.

[0011] Further, step S3 includes the following sub-steps: S31, dividing the partitioned carbon emission data subset into multiple time slices according to the time dimension, each time slice corresponding to the calibration process stage of the UHV project design and construction, and extracting the statistical features of the carbon emission data in each time slice; S32, mapping the carbon emission data in each time slice to the three-dimensional spatial coordinate system of the UHV project line according to the spatial dimension, and determining the spatial location coordinates and surrounding environmental parameters corresponding to the carbon emission data; S33, performing feature fusion on the carbon emission data of each spatiotemporal slice through a spatiotemporal coupled carbon source dynamic identification model, and establishing the correlation between the spatiotemporal dimension and the carbon emission intensity; S34, based on the correlation, selecting spatiotemporal regions where the carbon emission intensity exceeds a preset basic threshold, and marking these regions as potential carbon emission source areas.

[0012] Further, step S4 includes the following sub-steps: S41, performing feature standardization processing on the carbon emission data of the initially located potential carbon emission source areas, and extracting the mean, variance, extreme values, and rate of change characteristic parameters of the data; S42, inputting the standardized feature parameters into the carbon emission data anomaly detection clustering algorithm, setting the cluster radius and anomaly judgment threshold, and clustering the data; S43, identifying data points in the cluster groups that deviate from the cluster center by more than the anomaly judgment threshold, judging them as abnormal carbon emission data and removing them; S44, merging and classifying the clusters after removing abnormal data, and classifying and organizing the effective carbon emission sources according to carbon emission intensity and source type.

[0013] Further, S5 includes the following sub-steps: S51, importing the categorized and organized carbon emission source data into the construction carbon emission dynamic simulation analysis platform, and setting the simulation time span, process connection parameters, and environmental impact variables; S52, based on the process flow diagram of the UHV project design and construction, constructing a carbon emission simulation model including equipment operation, material consumption, and energy conversion; S53, inputting different control strategy parameters into the simulation model, starting dynamic simulation, and recording the carbon emission change data of each carbon emission source in real time during the simulation; S54, cross-validating the results of multiple simulations, and extracting the common characteristics and differentiated trends of carbon emission changes under different control strategies.

[0014] A method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage (UHV) power transmission projects is proposed. This method is implemented through different units, including: a multi-dimensional carbon emission data acquisition and transmission unit, which collects topography, equipment operating conditions, material consumption, energy consumption, and environmental parameters throughout the entire UHV project design and construction process via distributed monitoring terminals, converts the collected data into a standardized format, and transmits it to a data processing unit; a carbon emission data feature extraction and mapping unit, connected to the multi-dimensional carbon emission data acquisition and transmission unit, which extracts features and maps sources to the standardized data using a panoramic UHV carbon emission mapping model, and outputs a subset of carbon emission data; and a spatiotemporally coupled carbon source localization unit, connected to the carbon emission data feature extraction and mapping unit, which uses a spatiotemporally coupled carbon source dynamic identification model to locate the data subset. The system performs spatiotemporal decomposition and preliminary source location, outputting potential carbon emission source data; a carbon emission data anomaly detection and clustering unit, connected to the spatiotemporally coupled carbon source location unit, uses a carbon emission data anomaly detection and clustering algorithm to perform anomaly screening and clustering analysis on potential carbon emission source data, outputting valid carbon emission source data; a dynamic simulation and deduction unit, connected to the carbon emission data anomaly detection and clustering unit, uses a construction carbon emission dynamic simulation analysis platform to simulate and deduce control strategies for valid carbon emission source data, outputting carbon emission change trend data; and a dynamic control scheme generation unit, connected to the dynamic simulation and deduction unit, combines carbon emission control thresholds and source priority parameters to generate targeted control schemes based on simulation results, enabling dynamic control of carbon emission sources in the design and construction of UHV projects.

[0015] Beneficial Effects: This invention proposes a method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage (UHV) power transmission projects. Utilizing a multi-dimensional data acquisition mechanism and panoramic mapping model covering the entire design and construction process, it achieves deep correlation between carbon emission data and source types, breaking the limitations of single data or localized monitoring. Combined with spatiotemporal coupling dynamic identification technology, it comprehensively captures the differences in carbon emission contributions across different construction stages, regional locations, and equipment types, solving the problems of ambiguous source location and inaccurate type classification. Through anomaly detection clustering algorithms, a data filtering and classification mechanism is constructed to eliminate invalid and interfering data. Simultaneously, by leveraging a construction carbon emission dynamic simulation analysis platform, it fully considers the dynamic changes in operating parameters and environmental conditions, providing precise basis for the formulation of control strategies and compensating for the lack of flexibility and specificity in traditional control schemes. Its beneficial effects are manifested in the following ways: achieving accurate identification and location of carbon emission sources in UHV projects throughout the entire process, improving the effectiveness and reliability of carbon emission data, optimizing the adaptability of control strategies through dynamic simulation and deduction, ensuring the accurate implementation of control measures based on a multi-unit collaborative system architecture, forming a full-chain technical system covering data collection, source identification, anomaly screening, simulation and deduction, and control implementation, and significantly improving the precision and efficiency of carbon emission control in the design and construction phases of UHV projects. Attached Figure Description

[0016] Figure 1This is a flowchart illustrating the overall process of the method of the present invention.

[0017] Figure 2 This is a flowchart of method step S3 of the present invention; Figure 3 This is a flowchart of method step S4 of the present invention; Figure 4 This is a flowchart of step S5 of the method of the present invention; Figure 5 This is a diagram showing the unit composition for implementing the method of the present invention. Detailed Implementation

[0018] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] like Figure 1 As shown, the method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage (UHV) power transmission projects includes the following steps: S1, collecting topographic parameters of the line laying area, equipment installation parameters, construction machinery operation parameters, material consumption parameters, energy consumption type parameters, and environmental impact parameters through a carbon emission monitoring terminal throughout the entire UHV power transmission project design and construction process, and constructing a multi-dimensional raw carbon emission data set; S2, extracting carbon emission source features from the raw data set based on the UHV carbon emission panoramic mapping model, establishing a mapping relationship between carbon emission data and source type, and dividing the carbon emission data into subsets for the design and construction phases; S3, using a spatiotemporally coupled carbon source dynamic identification model to analyze the divided carbon emission data. The subset is decomposed into spatiotemporal dimensions to initially locate carbon emission sources for different construction procedures, equipment types, and regional locations; S4, anomaly detection and clustering algorithms are used to filter out outliers and perform clustering analysis on the initially located carbon emission source data, eliminating invalid data and classifying carbon emission sources of the same type; S5, a construction carbon emission dynamic simulation analysis platform is used to dynamically simulate and extrapolate the clustered carbon emission source data to simulate the carbon emission change trends under different control strategies; S6, based on the simulation results, combined with the carbon emission control threshold parameters of the UHV project and the source priority weight parameters, a targeted carbon emission source control scheme is generated to complete the dynamic control of carbon emission sources.

[0020] The implementation process of step S1 is as follows: Data acquisition work is initiated during the design and planning phase of the UHV project and continues until the completion of construction. A total of 120 distributed monitoring terminals are deployed, arranged at intervals of 5 kilometers along the line. Simultaneously, 20 fixed-point monitoring devices are added in key equipment installation areas, material storage sites, and energy supply stations. The collected topographic parameters include altitude, slope, soil type, and vegetation coverage along the line route. The altitude acquisition range is from -50 meters to 3000 meters, and the slope acquisition accuracy is to 1 degree. Equipment installation condition parameters include the installation operation time, operation intensity, and number of start-stop cycles for 30 types of core equipment such as transformers, reactors, and circuit breakers. Operation time is collected at the minute level, and the number of start-stop cycles is recorded in real time. Construction machinery operation parameters involve the operating time, power output, and operation frequency of 15 types of machinery such as tower cranes, excavators, and cranes. The operating time is accurate to the minute, and the power output is divided into 10 zones according to level. The data collection parameters include: material consumption parameters such as the quantity and usage progress of 25 major materials including steel, aluminum, and concrete, with daily consumption data; energy consumption type parameters include the consumption of electricity, diesel, and natural gas, with electricity consumption measured hourly and fuel and gas consumption recorded per transaction; environmental impact parameters include temperature, humidity, and wind speed, with temperature ranging from -40℃ to 60℃, humidity ranging from 10% to 95%, and wind speed ranging from 0 to 25 meters per second. All parameters are aggregated by the monitoring terminal to construct a multi-dimensional raw carbon emission data set, providing comprehensive data support for subsequent carbon emission source identification.

[0021] The implementation process of step S2 is as follows: The ultra-high voltage carbon emission panoramic mapping model is activated to process the original dataset. First, feature extraction is performed on the collected multi-dimensional data. The extracted carbon emission source features include data fluctuation amplitude, change trend, and correlation strength. Data fluctuation amplitude is calculated on an hourly basis, change trend is analyzed on a daily basis, and correlation strength is obtained through data correlation analysis. Based on the extracted features, a mapping association between carbon emission data and source type is established. A mapping association threshold of 0.85 is set; data exceeding this threshold are considered strongly correlated data. Subsequently, carbon emission data subsets were divided into design and construction phases. The design phase data subset includes carbon emission-related data generated during planning and design, scheme demonstration, and drawing preparation. Specifically, it includes parameters related to energy consumption, material preparation and planning, and equipment selection and evaluation during the design phase. A total of 8 core parameters were selected and included in the design phase subset. The construction phase data subset includes carbon emission data generated during foundation construction, equipment installation, line erection, and commissioning. It includes 12 core parameters such as construction machinery operation, on-site operation energy consumption, and actual material consumption. This division ensures the independence and specificity of the two data subsets, providing a clear data foundation for subsequent phased carbon emission source identification, improving the accuracy and efficiency of the identification process, and avoiding feature extraction bias caused by cross-interference of data from different phases.

[0022] The implementation process of step S3 is as follows: The spatiotemporal coupled carbon source dynamic identification model is called to perform spatiotemporal dimension decomposition on the two types of carbon emission data subsets after division. The time dimension decomposition is divided into 10 key nodes according to the construction progress. Each node corresponds to a different process stage. The decomposition accuracy is down to the day to ensure that the carbon emission data of each process stage is presented separately. The spatial dimension decomposition is divided into 30 regional segments according to the route. Each regional segment is 10 kilometers long. At the same time, each regional segment is further divided into three functional areas: equipment installation area, material storage area, and operation passage area, to achieve fine spatial division. By decomposing carbon emission data into spatiotemporal dimensions, the data is precisely mapped to specific time points and spatial regions. This allows for the analysis of the carbon emission contributions of different construction processes. Carbon emission data for 15 major processes, including foundation construction, equipment installation, and line erection, are statistically analyzed separately. The carbon emission differences among different equipment types are differentiated, and carbon emission data for 30 core equipment categories are categorized and calculated. The carbon emission distribution in different regions is clarified, and the total carbon emission and carbon emission intensity per unit area are statistically analyzed by region segment and functional area. Ultimately, this achieves preliminary location of carbon emission sources, determining the temporal distribution range, spatial coordinates, associated processes, and related equipment of potential carbon emission sources. This provides a preliminary basis for subsequent precise location and effectively narrows the search range for carbon emission sources.

[0023] The implementation process of step S4 is as follows: The carbon emission data anomaly detection clustering algorithm is activated to process the initially located carbon emission source data. First, the clustering radius of the algorithm is set to 5, and the anomaly judgment threshold is set to 3.2. Based on these parameters, the data is preprocessed to filter out valid data samples. Then, cluster analysis is performed on the data, dividing it into 8 clusters according to carbon emission intensity, data change patterns, and spatiotemporal distribution characteristics. Each cluster includes carbon emission data with similar characteristics. During the clustering process, the distance between each data point and the center of its respective cluster is calculated in real time. When the distance exceeds the anomaly judgment threshold, the data point is judged as an anomaly. Anomaly data mainly includes numerical mutations caused by monitoring equipment failure, invalid data caused by environmental interference, and biased data caused by human recording errors. This type of data accounts for approximately 3% to 5% of the total data volume and needs to be removed. After removing outlier data, the remaining valid data clusters are merged and classified. Carbon emission source data belonging to the same construction process, equipment type, and location are grouped into one category, resulting in 12 categories of carbon emission source types. This process effectively purifies the data quality, avoids interference from invalid data in subsequent analysis, and achieves accurate classification of carbon emission sources, providing high-quality data input for dynamic simulation and ensuring the reliability and accuracy of simulation results.

[0024] Step S5 is implemented as follows: The clustered carbon emission source data is imported into the construction carbon emission dynamic simulation analysis platform. First, simulation parameters are set, with the simulation time span consistent with the actual construction cycle of the project, set to a maximum of 18 months, and the time step set to 1 day. Process connection parameters are set according to the actual construction process sequence, including the interval time and overlap method between processes. Environmental impact variables are set with fluctuation ranges based on historical environmental data for the same period: temperature fluctuation ±5℃, humidity fluctuation ±10%, and wind speed fluctuation ±3 meters per second. Subsequently, based on the process flow diagram of the UHV project design and construction, a carbon emission simulation model is constructed within the platform. The model includes an equipment operation module, a material consumption module, and an energy conversion module. The equipment operation module records the carbon emission generation mechanisms of 15 types of construction machinery, the material consumption module includes the carbon emission release patterns of 25 major materials, and the energy conversion module includes the carbon emission conversion logic of 3 major energy sources. Then, eight different control strategy parameters are input, including equipment operation optimization parameters, material consumption control parameters, and energy substitution parameters. Dynamic simulation is then initiated, and the platform records hourly carbon emission changes at each carbon emission source in real time, generating a phased simulation report every 10 days. After the simulation, the simulation results under the eight control strategies are compared and analyzed. Characteristic parameters such as peak values, trends, and fluctuation amplitudes of carbon emission changes are extracted to clarify the impact of different control strategies on each carbon emission source, providing data support for the formulation of control plans and ensuring the scientific validity and effectiveness of the control strategies.

[0025] The implementation process of step S6 is as follows: Based on the simulation results of step S5, a control scheme is generated by combining the carbon emission control threshold parameters and source point priority weight parameters of the UHV project. First, carbon emission control thresholds are set, with differentiated thresholds set according to different construction stages. The control threshold for the design stage is set so that the total carbon emission in each stage does not exceed a certain fixed value. For the construction stage, thresholds are set according to the work process, with the highest threshold for foundation construction and the lowest for commissioning and operation. Source point priority weight parameters are divided into five levels based on carbon emission intensity, impact range, and control difficulty, with weight coefficients of 0.9, 0.7, 0.5, 0.3, and 0.1, respectively. Sources with carbon emission intensity exceeding 1000 units, impact range covering more than 5 kilometers, and low control difficulty are set as the highest priority. Subsequently, based on the carbon emission change trends under different control strategies in the simulation results, and combining the control thresholds and priority weights, eight control strategies are combined and optimized. For the highest priority source points, a combination strategy of equipment operation optimization + energy substitution is adopted; for medium priority source points, a combination strategy of material consumption control + work process adjustment is adopted; and for low priority source points, a simple monitoring and control strategy is adopted. Ultimately, a targeted carbon emission source control plan is generated. The plan clarifies the control measures, implementation time, responsible parties, and control objectives for each carbon emission source. After the plan is generated, it is simultaneously transmitted to the project management system to guide on-site construction personnel to implement the control measures according to the plan. Through this process, precise control of carbon emission sources is achieved, ensuring that the total carbon emissions of the project are controlled within the preset range, and improving the precision and efficiency of carbon emission control in UHV projects.

[0026] Preferably, the expression for the ultra-high voltage carbon emission panoramic mapping model is: ,in, This is the panoramic mapping coefficient for ultra-high voltage carbon emissions; For the i-th type of carbon emission source point weighting parameter; The carbon emission intensity parameter for the i-th type of source point; The duration parameter for the i-th type of source point; The terrain adaptation coefficient for the i-th type of source point; Let be the carbon emission coefficient of the i-th source material; The power weight of the j-th type of construction equipment; For the energy consumption parameters of the j-th type of construction equipment; Let J be the efficiency coefficient of the j-th type of construction procedure; is the correction factor for the design and construction phase; n is the total number of carbon emission source types; m is the total number of construction equipment types.

[0027] Specifically, the UHV carbon emission panoramic mapping model is based on the multi-factor coupling characteristics of UHV engineering carbon emissions. By analyzing the correlation between carbon emission source intensity, duration, and parameters such as terrain, materials, and equipment, it adopts a combination of weighted summation and radical correction. First, it quantifies and accumulates the carbon emission contributions of various source points, then introduces a comprehensive correction term for equipment energy consumption and process efficiency, and finally adapts the carbon emission characteristics of different engineering stages through stage correction coefficients to form a complete link. This formula recognizes that UHV carbon emissions are affected by multiple dimensions such as the characteristics of the source points themselves, the external environment, and construction conditions. It achieves panoramic mapping through multi-parameter coupling, and the setting of weighting coefficients and correction terms can balance the influence weight of different parameters. Source point weights are set from 0.1 to 0.9 based on their carbon emission contribution percentage. Carbon emission intensity parameters are calibrated based on historical data from similar projects. Terrain adaptability coefficients are set from 0.6 to 1.2 based on terrain type. Material carbon emission coefficients are determined with reference to industry standards. Equipment power weights are set from 0.3 to 0.8 based on equipment energy consumption levels. Process efficiency coefficients are set from 0.7 to 1.0 based on construction technology maturity. Stage correction coefficients are set at 0.8 for the design stage and 1.2 for the construction stage. During implementation, the model is first called to read various parameters, and the panoramic mapping coefficient is calculated using formulas. Carbon emission data subsets are then divided according to the coefficient values. This process integrates multi-dimensional data and extracts features, providing accurate data classification for subsequent source point identification. This ensures that carbon emission data of different stages and types are effectively distinguished, improving the overall technical solution's relevance and reliability.

[0028] Preferably, the expression for the spatiotemporally coupled carbon source dynamic identification model is: ,in, Spacetime coordinates The intensity of carbon source identification at the location; The spatial coupling coefficient; The time coupling coefficient; Let t be the carbon emission concentration parameter at time t; coordinates Distance attenuation coefficient at that location; This is a spatiotemporal coupling correction factor; For the k-th type of construction process, in coordinates Carbon emission contribution value at the location; is the sensitivity parameter for identifying the k-th type of carbon source point; p is the total number of construction procedures; t represents the spatial coordinate parameter; t represents the time parameter.

[0029] Specifically, the spatiotemporal coupled carbon source dynamic identification model takes spatiotemporal coupling as its core. It first constructs a correlation function between spatial coordinates and carbon emission concentration, then introduces a dynamic change term for the time variable, quantifies the spatiotemporal coupling strength through partial derivative calculations, and finally superimposes the carbon emission contribution of construction procedures to form a complete logic. The formula assumes that carbon emission sources in ultra-high voltage (UHV) projects exhibit significant spatiotemporal distribution differences, with the carbon emission intensity of the same source varying at different times and spatial locations, requiring precise location through spatiotemporal coupling analysis. The spatial coupling coefficient is set to 0.05 to 0.2 based on spatial resolution, the temporal coupling coefficient is set to 0.03 to 0.15 based on time sampling frequency, the carbon emission concentration parameter is obtained based on real-time monitoring data, the distance attenuation coefficient is set to 0.5 to 1.0 based on spatial distance, the spatiotemporal coupling correction factor is set to 0.8 to 1.3 based on project complexity, the carbon emission contribution value of construction procedures is set to 10% to 50% based on the proportion of energy consumption in each procedure, and the carbon source identification sensitivity parameter is set to 0.7 to 0.95 based on identification accuracy requirements. During implementation, a subset of data is first input into the model, and spatiotemporal parameters and process parameters are substituted. The carbon source identification intensity under each spatiotemporal coordinate is calculated through formulas. Potential source areas are screened based on the intensity threshold. This process achieves in-depth analysis of the spatiotemporal dimension, effectively captures the carbon emission source characteristics under different spatiotemporal conditions, solves the problem of ambiguous source location in traditional technologies, and provides accurate source location information for subsequent precise control.

[0030] Preferably, the expression for the carbon emission data anomaly detection clustering algorithm is: ,in, For carbon emission data cluster center parameters; This represents the q-th carbon emission data sample value; Let q be the anomaly detection coefficient for the q-th data point; The weight of the q-th data density; Let r be the initial center of the r-th cluster; Let r be the distance parameter within the r-th cluster; Let be the similarity coefficient of the r-th cluster; Let t be the error value of the t-th data point; Let t be the error weight; This is the vth valid data value; is the correlation coefficient of the v-th data point; q is the total number of data samples; s is the number of clusters; u is the number of error data points; This represents the number of valid data points.

[0031] Specifically, the carbon emission data anomaly detection clustering algorithm follows the logic of data feature quantification, anomaly judgment, and cluster grouping. First, it multiplies and accumulates the carbon emission data sample values, anomaly coefficients, and density weights to obtain the effective feature values. Then, it constructs a denominator correction term through the multiplication and accumulation of cluster parameters. Finally, it introduces the ratio of the error to the cubic root of the effective data as an anomaly screening factor. The formula assumes that a large amount of invalid and abnormal data exists in the carbon emission data, requiring clustering algorithms to classify effective data and remove abnormal data to ensure the accuracy of subsequent analysis. The data sample values ​​are directly obtained from monitoring data. The anomaly judgment coefficient is set to 0.1 to 0.3 according to the allowable range of data fluctuation. The data density weight is set to 0.6 to 1.0 according to the data distribution density. The initial cluster center is set to 5 to 15 according to the data distribution peak value. The distance parameter within the cluster is set to 2 to 8 according to the clustering accuracy. The cluster similarity coefficient is set to 0.7 to 0.9 according to the similarity requirement. The data error value is set to 1 to 5 according to the monitoring accuracy. The error weight is set to 0.2 to 0.6 according to the degree of error impact. The effective data values ​​are calibrated based on normal operating condition data. The data correlation coefficient is set to 0.6 to 0.95 according to the data association strength. During implementation, the source point data of the initial positioning is input first. After setting the parameters, the cluster center parameters are calculated by formula. Clusters are divided according to the parameters, and abnormal data that deviates from the center are removed. This process achieves data quality purification and effective classification, ensuring that the data input into the subsequent simulation platform has high reliability and avoiding interference from abnormal data in the formulation of control strategies.

[0032] Preferably, the carbon emission trend projection expression of the construction carbon emission dynamic simulation analysis platform is as follows: ,in, for Simulated carbon emissions values ​​at any given time; For the simulation adaptation coefficients of the mapping model; To identify the simulation weight coefficients of the model; These are the correction coefficients for the clustering algorithm simulation. These are the error parameters for the simulation system; For Category O control measures The execution intensity parameter at any given time; Total number of control measures types; This is the simulation time step; This is the time variable for integration.

[0033] Specifically, the carbon emission trend projection of the construction carbon emission dynamic simulation analysis platform adopts a multi-model fusion approach. First, it integrates linear combinations of panoramic mapping coefficients, carbon source identification intensity, and cluster center parameters. Through integral calculations, it accumulates the carbon emission trend over time. Then, it introduces a correction factor based on the product of simulation error parameters and the intensity of control measure implementation. The formula assumes that the effectiveness of control strategies is comprehensively affected by the output results of multiple models and dynamic operating conditions. Therefore, it is necessary to simulate carbon emission changes under different control strategies by fusing multi-model parameters and dynamic simulation technology. The simulation adaptation coefficient of the mapping model is set to 0.7 to 1.1 based on model fit; the simulation weight coefficient of the identification model is set to 0.8 to 1.2 based on identification accuracy; the simulation correction coefficient of the clustering algorithm is set to 0.6 to 1.0 based on clustering effect; the simulation system error parameter is set to 0.05 to 0.15 based on simulation accuracy requirements; and the control measure implementation intensity parameter is set to 0.5 to 1.0 based on the implementation strength of the measures. During implementation, effective carbon emission source data are first input into the simulation platform, the simulation time step and integral variables are set, various model parameters and control measure parameters are substituted, and carbon emission simulation values ​​at different times are calculated through formulas. Simulation data is recorded in real time and periodic reports are generated. This process realizes dynamic simulation and effect prediction of control strategies, provides data support for subsequent optimization of control plans, and ensures the scientificity and effectiveness of control measures.

[0034] Preferably, the expression for the generation model of the carbon emission source control scheme for the design and construction of the ultra-high voltage project is: ,in, Parameters for carbon emission source control strategies; This is the source point priority coefficient; The intensity of implementation of the h-th type of control strategy; The technical efficiency parameter for the h-th type of control strategy; This represents the total number of control strategy types.

[0035] Specifically, the carbon emission source control scheme generation model for ultra-high voltage (UHV) power transmission projects is based on "source priority, multi-model parameter fusion, and control strategy optimization." First, the source priority coefficient is multiplied by the carbon source identification intensity and the panoramic mapping coefficient to obtain the comprehensive carbon emission impact value of the source. Then, it is corrected by using the square root of the cluster center parameter and the simulation value. Finally, the multiplicative summation of the implementation intensity and technical efficiency of various control strategies is added. The formula is designed to ensure that the control scheme is tailored to the source importance, multi-model analysis results, and the effectiveness of the control strategies. The source priority coefficient is set from 0.1 to 0.9 according to the source importance level. The strategy implementation intensity is set at 0.3 to 0.9 based on the strength of the measures, and the technical efficiency parameter is set at 0.6 to 0.95 based on the actual effect of the strategy. During implementation, the output parameters of multiple models and the source priority parameters are first read and substituted into the formula to calculate the control strategy parameters. Based on the parameter values, corresponding control strategy combinations are selected, and differentiated solutions are developed for different priority sources. Each solution clearly defines the control measures, implementation time, responsible parties, and control objectives. This process achieves precise matching and optimized combination of control strategies, effectively improving the implementation effect of control measures, ensuring that the total carbon emissions of the project are controlled within the preset range, and solving the problem of traditional control solutions lacking specificity.

[0036] Preferred, such as Figure 2 As shown, step S3 includes the following sub-steps: S31, dividing the partitioned carbon emission data subset into multiple time slices according to the time dimension, each time slice corresponding to the calibration process stage of the UHV project design and construction, and extracting the statistical features of the carbon emission data in each time slice; S32, mapping the carbon emission data in each time slice to the three-dimensional spatial coordinate system of the UHV project line according to the spatial dimension, and determining the spatial location coordinates and surrounding environmental parameters corresponding to the carbon emission data; S33, performing feature fusion on the carbon emission data of each spatiotemporal slice through a spatiotemporal coupled carbon source dynamic identification model, and establishing the correlation between the spatiotemporal dimension and the carbon emission intensity; S34, based on the correlation, selecting spatiotemporal regions where the carbon emission intensity exceeds a preset basic threshold, and marking these regions as potential carbon emission source areas.

[0037] Specifically, step S3 includes: S31 First, the divided carbon emission data subset is sliced ​​according to the time dimension. The time slices are divided according to the process stage division standard of UHV project design and construction, and a total of 10 time slices are divided. Each time slice corresponds to 2 to 3 consecutive processes. The slice duration is set to 7 to 30 days according to the process complexity. Statistical features of carbon emission data in each time slice are extracted, including core feature parameters such as total data volume, variation range, frequency of peak occurrence, and mean level, to provide basic time dimension data for subsequent spatiotemporal coupling analysis; S32 According to the spatial dimension, the carbon emission data in each time slice is mapped to the three-dimensional spatial coordinate system of the UHV project line. The coordinate system takes the starting point of the project as the origin, the X-axis along the line direction, the Y-axis perpendicular to the line laterally, and the Z-axis as the altitude. The spatial coordinate accuracy is set to 10 meters. At the same time, the surrounding environmental parameters corresponding to each coordinate point are extracted, including vegetation cover density, terrain slope, and surrounding buildings. The system uses building distribution density and other parameters to accurately bind carbon emission data with spatial location and environmental conditions. S33 calls a spatiotemporally coupled carbon source dynamic identification model to perform feature fusion on the carbon emission data of each spatiotemporal slice. During the fusion process, the spatial feature weight is set to 0.6 and the temporal feature weight to 0.4. A quantitative correlation between spatiotemporal dimensions and carbon emission intensity is established through feature overlay and correlation operations. The correlation operation iteration count is set to 50 times to ensure the stability of the correlation results. S34 sets a basic threshold for carbon emission intensity based on the established correlation relationship. This threshold is set to 20 to 50 according to the environmental standards of the project area and the project scale. Spatiotemporal areas with carbon emission intensity exceeding this threshold are selected and marked as potential carbon emission source areas. The minimum delineation range for each potential area is 100 square meters. These four steps achieve the initial positioning of carbon emission sources, laying the foundation for subsequent accurate identification and effectively improving the comprehensiveness and accuracy of source location.

[0038] Preferred, such as Figure 3 As shown, step S4 includes the following sub-steps: S41, performing feature standardization processing on the carbon emission data of the initially located potential carbon emission source areas, and extracting the mean, variance, extreme values, and rate of change characteristic parameters of the data; S42, inputting the standardized feature parameters into the carbon emission data anomaly detection clustering algorithm, setting the cluster radius and anomaly judgment threshold, and clustering the data; S43, identifying data points in the cluster groups that deviate from the cluster center by more than the anomaly judgment threshold, judging them as abnormal carbon emission data and removing them; S44, merging and classifying the clusters after removing abnormal data, and classifying and organizing the effective carbon emission sources according to carbon emission intensity and source type.

[0039] Specifically, step S4 includes S41, which involves standardizing the carbon emission data of the initially identified potential carbon emission source areas. This standardization process first compresses the data range, mapping all data to a value range of 0 to 1. Then, it extracts four core feature parameters: mean, variance, extreme values, and rate of change. The mean is calculated using a sliding window method with a window size of 20 data points. Variance is calculated by performing a sum of squared deviations based on the mean. Extreme values ​​are extracted as the maximum and minimum values ​​within each potential area. The rate of change is calculated based on the hourly data difference, ensuring that the feature parameters comprehensively reflect the essential attributes of the data. S42, the standardized feature parameters are input into a carbon emission data anomaly detection clustering algorithm. The clustering radius is set to 5, determined based on the data feature dimension and distribution density. The anomaly detection threshold is set to 3.2, derived through statistical analysis of similar engineering data, effectively distinguishing between normal and abnormal data. The algorithm then clusters the data, grouping them according to specific characteristics. The similarity of data points is automatically aggregated to form multiple independent clusters. S43 calculates the Euclidean distance between each data point and the center of its cluster in real time. When the calculated distance exceeds the set anomaly judgment threshold, the data point is judged as abnormal carbon emission data. During the judgment process, the generation time, spatial location and corresponding feature parameters of the abnormal data are recorded simultaneously. Then, the abnormal data is removed from the data set through a data filtering mechanism, with the removal ratio controlled at 3% to 5% of the total data volume. S44 merges and classifies the effective clusters after removing abnormal data. The merging condition is that the distance between the cluster centers is less than 2.5. The classification is based on two core indicators: carbon emission intensity and source type. Carbon emission intensity is divided into 10 levels, and source type is divided into three major categories and 12 subcategories: equipment operation, material consumption and energy consumption. Through these four steps, the data quality is purified and the carbon emission source points are accurately classified, providing high-quality data input for subsequent dynamic simulation and ensuring the reliability of the simulation results.

[0040] Preferred, such as Figure 4 As shown, S5 includes the following sub-steps: S51, importing the categorized and organized carbon emission source data into the construction carbon emission dynamic simulation analysis platform, and setting the simulation time span, process connection parameters, and environmental impact variables; S52, based on the process flow diagram of the UHV project design and construction, constructing a carbon emission simulation model including equipment operation, material consumption, and energy conversion; S53, inputting different control strategy parameters into the simulation model, starting dynamic simulation, and recording the carbon emission change data of each carbon emission source in real time during the simulation; S54, cross-validating the results of multiple simulations, and extracting the common characteristics and differentiated trends of carbon emission changes under different control strategies.

[0041] Specifically, step S5 includes S51, importing the categorized and organized carbon emission source data into the construction carbon emission dynamic simulation analysis platform. First, core simulation parameters are set, with the simulation time span consistent with the actual construction cycle, set to a maximum of 18 months, and the time step set to 1 day to ensure the time accuracy of the simulation results. Process connection parameters are set according to the actual construction process sequence, including intervals between processes of 2 to 5 days, and overlapping methods of parallel or sequential overlapping. Environmental impact variables are set with fluctuation ranges based on environmental data from the same period in the past 5 years for the project area, with temperature fluctuations of ±5℃ and humidity fluctuations... The simulation range is ±10%, and the wind speed fluctuation range is ±3 meters per second, providing realistic environmental conditions for the simulation. Based on the detailed process flow diagram of UHV engineering design and construction, S52 constructs a complete carbon emission simulation model within the platform. The model includes three core modules: equipment operation, material consumption, and energy conversion. The equipment operation module records the carbon emission generation mechanisms of 15 types of construction machinery, setting the calculation logic according to the correlation between machinery operating power and duration. The material consumption module includes the carbon emission release patterns of 25 major materials, setting parameters according to material usage and release rate. The energy conversion module includes electricity, diesel... The model incorporates carbon emission conversion logic for the three main energy sources—oil, natural gas, and carbon dioxide—ensuring a comprehensive simulation of carbon emission generation. S53 inputs eight different control strategy parameters into the simulation model, including equipment operation optimization parameters, material consumption control parameters, and energy substitution parameters. Each parameter category includes five to eight specific control indicators. Dynamic simulation is then initiated, with the platform calculating and recording hourly carbon emission changes at each source point according to a set time step. A phased simulation report is generated every 10 days, including core indicators such as total carbon emissions, peak values, and trends. S54 analyzes the results of multiple simulations. Cross-validation was conducted by comparing carbon emission data from the same source under different control strategies and verifying the consistency of simulation results from different simulation runs under the same control strategy. The confidence level for cross-validation was set at 95%. Then, common characteristics of carbon emission changes under different control strategies were extracted, including the rate of carbon emission decline and the duration of the stabilization period, as well as differentiated trends, including differences in the sensitivity of different sources to control strategies. Through these four steps, dynamic simulation and effect prediction of control strategies were achieved, providing scientific and accurate data support for the formulation of subsequent control plans and ensuring the pertinence and effectiveness of control measures.

[0042] like Figure 5As shown, a method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage (UHV) power transmission projects is implemented through different units, including: a multi-dimensional carbon emission data acquisition and transmission unit, used to collect topography, equipment operating conditions, material consumption, energy consumption, and environmental parameters throughout the entire UHV project design and construction process via distributed monitoring terminals, converting the collected data into a standardized format and transmitting it to a data processing unit; a carbon emission data feature extraction and mapping unit, connected to the multi-dimensional carbon emission data acquisition and transmission unit, which extracts features and maps sources from the standardized data using a panoramic UHV carbon emission mapping model, outputting a subset of carbon emission data; and a spatiotemporally coupled carbon source localization unit, connected to the carbon emission data feature extraction and mapping unit, which uses a spatiotemporally coupled carbon source dynamic identification model to locate the carbon emission sources in the data. The subset performs spatiotemporal decomposition and preliminary source location, outputting potential carbon emission source data; the carbon emission data anomaly detection and clustering unit, connected to the spatiotemporally coupled carbon source location unit, performs anomaly screening and cluster analysis on potential carbon emission source data through a carbon emission data anomaly detection and clustering algorithm, outputting valid carbon emission source data; the dynamic simulation and deduction unit, connected to the carbon emission data anomaly detection and clustering unit, uses the construction carbon emission dynamic simulation analysis platform to simulate and deduce control strategies for valid carbon emission source data, outputting carbon emission change trend data; the dynamic control scheme generation unit, connected to the dynamic simulation and deduction unit, combines carbon emission control thresholds and source priority parameters, and generates targeted control schemes based on simulation results to dynamically control carbon emission sources in the design and construction of UHV projects.

[0043] The formula in this invention integrates different scalar and vector parameters for unified calculation. Through standardization, weight allocation, dimension adaptation, and coupling correction mechanisms, it eliminates differences in parameter attributes and constructs a quantitative correlation foundation for multi-dimensional parameters. For scalar parameters, such as carbon emission intensity, duration, and material consumption, the values ​​are directly calibrated based on actual engineering conditions and industry standards. Linear transformation maps scalar parameters of different magnitudes to the same numerical range, ensuring that the parameter contribution can be quantitatively compared. For vector parameters, such as spatial coordinates, spatiotemporal coupling strength, and carbon emission change trends, the vector features are transformed into a calculable scalar form by extracting the vector's magnitude, directional components, or dynamic rate of change. Simultaneously, weight coefficients are set based on the actual role of the parameters in carbon emission identification and control, such as spatial feature weights and temporal feature weights, to balance the influence of different attribute parameters. For example, vector parameters such as spatial coordinates are extracted using 3D coordinate system transformation to obtain scalar features like distance and altitude, which are then incorporated into the calculation along with scalar parameters like carbon emission intensity. Spatiotemporal coupling intensity vectors are decomposed into spatially correlated components and temporally dynamic components, and after weighting, are integrated with scalar parameters such as equipment energy consumption and material carbon emission coefficients. Furthermore, the correction factors and adaptation coefficients set in the formulas further calibrate the computational compatibility of different attribute parameters, ensuring that scalar and vector parameters achieve logically self-consistent coupling operations within the same computational framework. This comprehensively covers the multi-dimensional influencing factors of carbon emission control in UHV projects, improving the overall adaptability of the model and algorithm.

[0044] This method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage (UHV) power transmission projects addresses the issues of ambiguous source location and inaccurate classification. It utilizes a multi-dimensional data acquisition mechanism covering the entire design and construction process, integrating diverse parameters such as terrain, equipment, materials, and energy. A panoramic mapping model is used to establish a deep correlation between carbon emission data and source type. Furthermore, spatiotemporal coupling dynamic identification technology comprehensively captures the differences in carbon emission contributions across different construction stages, locations, and equipment types, overcoming the limitations of single data or localized monitoring and achieving precise location and classification of carbon emission sources. Addressing the lack of flexibility and specificity in traditional control schemes, an efficient data filtering and classification mechanism is constructed using anomaly detection clustering algorithms to eliminate invalid and interfering data. Simultaneously, a construction carbon emission dynamic simulation analysis platform is used to fully consider the dynamic changes in operating parameters and environmental conditions, providing accurate and dynamic basis for control strategy formulation and ensuring a high degree of adaptation between the control scheme and the actual needs of the project.

[0045] This method achieves comprehensiveness and accuracy in carbon emission source identification. Through multi-dimensional data collection and multi-model collaborative application, it covers carbon emission sources throughout the entire process of UHV engineering design and construction, avoiding omissions or misjudgments. It improves the effectiveness and reliability of carbon emission data processing by purifying data quality through anomaly detection and clustering technology, providing solid data support for subsequent analysis and control. It enhances the dynamism and adaptability of control strategies by simulating carbon emission changes under different scenarios using dynamic simulation and extrapolation technology, ensuring that control measures can respond to dynamic adjustments in engineering conditions. It constructs a closed-loop control system, forming a complete chain from data collection, source identification, anomaly screening to simulation and extrapolation, and control implementation. Relying on a multi-unit collaborative architecture, it ensures the efficient implementation of control measures, significantly improving the precision and practical effectiveness of carbon emission control in UHV engineering.

[0046] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," "link," and "fix" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0047] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects, characterized in that... Includes the following steps: S1. A multi-dimensional raw carbon emission data set is constructed by collecting topographic parameters of the line laying area, equipment installation parameters, construction machinery operation parameters, material consumption parameters, energy consumption type parameters, and environmental impact parameters through a carbon emission monitoring terminal throughout the design and construction process of the UHV project. S2. Based on the UHV carbon emission panoramic mapping model, carbon emission source features are extracted from the raw data set, establishing a mapping relationship between carbon emission data and source types, and dividing the carbon emission data into subsets for the design and construction phases. S3. A spatiotemporal coupled carbon source dynamic identification model is used to decompose the divided carbon emission data subsets in a spatiotemporal dimension, and different construction phases are then applied. S4. Initially locate carbon emission sources based on construction processes, different equipment types, and different regional locations; S5. Use a carbon emission data anomaly detection clustering algorithm to filter out outliers and perform cluster analysis on the initially located carbon emission source data, eliminating invalid data and classifying carbon emission sources of the same type; S6. Use a construction carbon emission dynamic simulation analysis platform to perform dynamic simulation and extrapolation on the clustered carbon emission source data, simulating the carbon emission change trends under different control strategies; S7. Based on the simulation results, combined with the carbon emission control threshold parameters of the UHV project and the source priority weight parameters, generate a targeted carbon emission source control plan to complete the dynamic control of carbon emission sources.

2. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, The expression for the ultra-high voltage carbon emission panoramic mapping model is: ,in, This is the panoramic mapping coefficient for ultra-high voltage carbon emissions; For the i-th type of carbon emission source point weighting parameter; The carbon emission intensity parameter for the i-th type of source point; The duration parameter for the i-th type of source point; The terrain adaptation coefficient for the i-th type of source point; Let be the carbon emission coefficient of the i-th source material; The power weight of the j-th type of construction equipment; For the energy consumption parameters of the j-th type of construction equipment; Let J be the efficiency coefficient of the j-th type of construction procedure; is the correction factor for the design and construction phase; n is the total number of carbon emission source types; m is the total number of construction equipment types.

3. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, The expression for the spatiotemporally coupled carbon source dynamic identification model is: ,in, Spacetime coordinates The intensity of carbon source identification at the location; The spatial coupling coefficient; The time coupling coefficient; Let t be the carbon emission concentration parameter at time t; coordinates Distance attenuation coefficient at that location; This is a spatiotemporal coupling correction factor; For the k-th type of construction process, in coordinates Carbon emission contribution value at the location; is the sensitivity parameter for identifying the k-th type of carbon source point; p is the total number of construction procedures; t represents the spatial coordinate parameter; t represents the time parameter.

4. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, The expression for the carbon emission data anomaly detection clustering algorithm is as follows: ,in, For carbon emission data cluster center parameters; This represents the q-th carbon emission data sample value; Let q be the anomaly detection coefficient for the q-th data point; The weight of the q-th data density; Let r be the initial center of the r-th cluster; Let r be the distance parameter within the r-th cluster; Let be the similarity coefficient of the r-th cluster; Let t be the error value of the t-th data point; Let t be the error weight; This is the vth valid data value; is the correlation coefficient of the v-th data point; q is the total number of data samples; s is the number of clusters; u is the number of error data points; This represents the number of valid data points.

5. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, The carbon emission trend projection expression of the construction carbon emission dynamic simulation analysis platform is as follows: ,in, for Simulated carbon emissions values ​​at any given time; For the simulation adaptation coefficients of the mapping model; To identify the simulation weight coefficients of the model; These are the correction coefficients for the clustering algorithm simulation. These are the error parameters for the simulation system; For Category O control measures The execution intensity parameter at any given time; Total number of control measures types; This is the simulation time step; This is the time variable for integration.

6. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, The expression for the generation model of the carbon emission source control scheme for the design and construction of ultra-high voltage projects is as follows: ,in, Parameters for carbon emission source control strategies; This is the source point priority coefficient; The intensity of implementation of the h-th type of control strategy; The technical efficiency parameter for the h-th type of control strategy; This represents the total number of control strategy types.

7. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, S3 includes the following steps: S31, dividing the divided carbon emission data subset into multiple time slices according to the time dimension, each time slice corresponding to the calibration process stage of the UHV project design and construction, and extracting the statistical features of carbon emission data in each time slice. S32, Map carbon emission data in each time slice to the three-dimensional spatial coordinate system of the UHV transmission line according to the spatial dimension, and determine the spatial location coordinates and surrounding environmental parameters corresponding to the carbon emission data; S33, Perform feature fusion on the carbon emission data of each spatiotemporal slice through a spatiotemporal coupled carbon source dynamic identification model, and establish the correlation between spatiotemporal dimension and carbon emission intensity; S34, Based on the correlation, screen out spatiotemporal regions where carbon emission intensity exceeds a preset basic threshold, and mark the region as a potential carbon emission source region.

8. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, S4 includes the following sub-steps: S41, performing feature standardization processing on the carbon emission data of the initially located potential carbon emission source areas, and extracting the mean, variance, extreme values, and rate of change feature parameters of the data; S42, inputting the standardized feature parameters into the carbon emission data anomaly detection clustering algorithm, setting the cluster radius and anomaly judgment threshold, and clustering the data; S43, identifying data points in the cluster groups that deviate from the cluster center by more than the anomaly judgment threshold, judging them as abnormal carbon emission data and removing them; S44, merging and classifying the clusters after removing abnormal data, and classifying and organizing the effective carbon emission sources according to carbon emission intensity and source type.

9. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to claim 1, characterized in that, S5 includes the following steps: S51, importing the categorized carbon emission source data into the construction carbon emission dynamic simulation analysis platform, and setting the simulation time span, process connection parameters, and environmental impact variables; S52, based on the process flow diagram of the UHV project design and construction, constructing a carbon emission simulation model including equipment operation, material consumption, and energy conversion; S53, inputting different control strategy parameters into the simulation model, starting dynamic simulation, and recording the carbon emission change data of each carbon emission source in real time during the simulation; S54, cross-validating the results of multiple simulations, and extracting the common characteristics and differentiated trends of carbon emission changes under different control strategies.

10. The method for identifying and controlling carbon emission sources during the design and construction of ultra-high voltage power transmission projects according to any one of claims 1-9, characterized in that, This method is implemented through different units, including: a multi-dimensional carbon emission data acquisition and transmission unit, used to collect topography, equipment conditions, material consumption, energy consumption, and environmental parameters throughout the design and construction process of ultra-high voltage (UHV) projects via distributed monitoring terminals, converting the collected data into a standardized format and transmitting it to the data processing unit; a carbon emission data feature extraction and mapping unit, connected to the multi-dimensional carbon emission data acquisition and transmission unit, which extracts features and maps source points from the standardized data using an UHV carbon emission panoramic mapping model, outputting a subset of carbon emission data; and a spatiotemporally coupled carbon source localization unit, connected to the carbon emission data feature extraction and mapping unit, which uses a spatiotemporally coupled carbon source dynamic identification model to perform spatiotemporal decomposition of the data subset and preliminary source point identification. The system comprises four main components: a carbon emission source location unit, which locates and outputs data on potential carbon emission sources; a carbon emission data anomaly detection and clustering unit, connected to the spatiotemporally coupled carbon source location unit, which uses a carbon emission data anomaly detection and clustering algorithm to perform anomaly screening and clustering analysis on potential carbon emission source data and outputs valid carbon emission source data; a dynamic simulation and deduction unit, connected to the carbon emission data anomaly detection and clustering unit, which uses a construction carbon emission dynamic simulation analysis platform to simulate and deduce control strategies for valid carbon emission source data and outputs carbon emission change trend data; and a dynamic control scheme generation unit, connected to the dynamic simulation and deduction unit, which combines carbon emission control thresholds and source priority parameters to generate targeted control schemes based on simulation results, enabling dynamic control of carbon emission sources in the design and construction of UHV projects.

Images