Subway construction carbon emission reduction management method under dynamic time sequence

Abstract

The invention provides a subway construction carbon emission reduction management method under a dynamic time sequence, and relates to the technical field of carbon emission reduction management, and the method comprises the steps: calculating an energy consumption prediction data set through the dynamic time sequence analysis, setting a carbon emission reduction target, formulating a plurality of carbon emission reduction management schemes, carrying out the carbon emission simulation analysis, and carrying out the carbon emission evaluation. Traversing the carbon emission reduction management schemes for screening, building a carbon emission data monitoring platform, executing the first carbon emission management scheme for real-time acquisition, tracking, dynamically adjusting the first carbon emission management scheme, and performing intelligent carbon emission reduction management. According to the invention, the technical problem of poor energy utilization efficiency caused by lack of dynamic adjustment of carbon emission reduction management according to different stages in the prior art can be solved, delicacy management is carried out on carbon emission reduction in different stages in the subway construction process by using dynamic time sequence analysis, more efficient carbon emission reduction management is realized, and the energy utilization efficiency is improved. And the energy utilization efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of carbon emission reduction management, and in particular to a method for managing carbon emission reduction in subway construction under dynamic time sequence. Background Art

[0002] With the acceleration of urbanization, subways, as an important means of public transportation, are growing in scale and speed. However, the carbon emissions generated during subway construction are becoming increasingly serious, causing significant impacts on the environment. The rail transit industry is promoting changes in the energy structure, especially by using renewable energy to reduce carbon emissions. For example, using renewable energy such as solar energy and wind energy to supply electricity will help achieve the integrated development of rail transit and renewable energy, optimize the energy structure of the transportation system, and promote the development of green, low-carbon, and environmentally friendly transportation systems. In the process of subway construction, environmental impact assessment and emission reduction benefit research are key steps, including quantitative analysis of resource and energy consumption intensity during subway construction. In the existing subway construction process, carbon emissions mainly come from the production and transportation of building materials, as well as energy consumption during construction. Energy consumption may vary at different stages of subway construction. Existing technologies often use a fixed construction schedule, without fully considering environmental factors and energy consumption at each stage, resulting in actual energy consumption not meeting expected targets, which in turn affects the overall emission reduction effect.

[0003] In summary, the existing technology has a technical problem that the energy utilization efficiency is poor due to the lack of dynamic adjustment of carbon emission reduction management according to different stages. Summary of the invention

[0004] The purpose of this application is to provide a carbon emission reduction management method for subway construction under dynamic time sequence, so as to solve the technical problem in the prior art that the energy utilization efficiency is poor due to the lack of dynamic adjustment of carbon emission reduction management according to different stages.

[0005] In view of the above problems, the present application provides a method for managing carbon emission reduction in subway construction under dynamic time series, wherein the method for managing carbon emission reduction in subway construction under dynamic time series includes: using dynamic time series analysis to calculate an energy consumption prediction data set for subway construction and operation, and setting a carbon emission reduction target based on the energy consumption prediction data set; planning based on the carbon emission reduction target and the energy consumption prediction data set, and formulating multiple carbon emission reduction management plans; executing the multiple carbon emission reduction management plans to perform carbon emission simulation analysis, and generate multiple simulation analysis results, and the multiple simulation analysis results correspond to the multiple carbon emission reduction management plans; performing carbon emission evaluation on the multiple simulation analysis results based on the carbon emission reduction target, traversing the multiple carbon emission reduction management plans according to the evaluation results, and determining a first carbon emission management plan; building a full life cycle carbon emission data monitoring platform, executing the first carbon emission management plan for real-time collection, and generating a real-time carbon emission data set; tracking according to the real-time carbon emission data set, dynamically adjusting the first carbon emission management plan according to the tracking feedback data set, and performing intelligent carbon emission reduction management for subway construction according to the adjustment results.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By using dynamic time series analysis to calculate the energy consumption forecast data set of subway construction and operation, the carbon emission reduction target is set according to the energy consumption forecast data set; based on the carbon emission reduction target and the energy consumption forecast data set, planning is carried out to formulate multiple carbon emission reduction management plans; the multiple carbon emission reduction management plans are executed to perform carbon emission simulation analysis to generate multiple simulation analysis results, and the multiple simulation analysis results correspond to the multiple carbon emission reduction management plans; based on the carbon emission reduction target, the multiple simulation analysis results are evaluated for carbon emission, and the multiple carbon emission reduction management plans are traversed according to the evaluation results to screen and determine the first carbon emission management plan; a full life cycle carbon emission data monitoring platform is built, the first carbon emission management plan is executed for real-time collection to generate a real-time carbon emission data set; tracking is carried out according to the real-time carbon emission data set, the first carbon emission management plan is dynamically adjusted according to the tracking feedback data set, and intelligent carbon emission reduction management is carried out for subway construction according to the adjustment results. In other words, by using dynamic time series analysis, the carbon emission reduction at different stages of the subway construction process is finely managed, multiple management plans are formulated and simulated and analyzed, and the best emission reduction strategy is determined, so as to achieve more efficient carbon emission reduction management and improve energy utilization efficiency.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 A flowchart of a method for managing carbon emission reduction in subway construction under a dynamic time sequence is provided for this application;

[0011] Figure 2 This is a flow chart of determining a first carbon emission management scheme in a carbon emission reduction management method for subway construction under a dynamic time sequence of this application. DETAILED DESCRIPTION

[0012] This application provides a method for managing carbon emission reduction in subway construction under dynamic time series, which solves the technical problem in the prior art that carbon emission reduction management lacks dynamic adjustment according to different stages, resulting in poor energy utilization efficiency. By using dynamic time series analysis, carbon emission reduction at different stages of subway construction is managed in a refined manner, multiple management plans are formulated and simulated and analyzed, and the best emission reduction strategy is determined, achieving more efficient carbon emission reduction management and improving energy utilization efficiency.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] For examples, please see the attached Figure 1 The present application provides a method for managing carbon emission reduction in subway construction under a dynamic time sequence, wherein the method for managing carbon emission reduction in subway construction under a dynamic time sequence specifically includes the following steps:

[0015] Step 1: Calculate the energy consumption prediction data set of subway construction and operation using dynamic time series analysis, and set carbon emission reduction targets based on the energy consumption prediction data set.

[0016] Specifically, collect historical energy consumption data during the construction and operation of the subway, including but not limited to the use of electricity, fuel oil, natural gas and other energy sources. The construction and operation of the subway covers different construction stages, such as civil engineering, tunnel excavation, track laying, station decoration, etc. When collecting historical energy consumption data, it is necessary to record the timestamp of the data. Analyze the historical energy consumption data, determine the specific source of energy consumption, and determine which construction stage the energy consumption belongs to. Preprocess the energy consumption data, including data cleaning and data normalization, and sort and divide it according to the order of subway construction and operation, and divide the energy consumption data according to the stage of subway construction and operation to which it belongs. Select a suitable time series model, such as LSTM, and input the divided data into the trained dynamic time series analysis model for prediction to obtain an energy consumption prediction data set.

[0017] The carbon emission coefficient is obtained based on the historical data of carbon emission influencing factors, and combined with the forecast of future energy consumption, the future carbon emissions are estimated. Use time series analysis algorithms, such as the ARIMA model, to model the carbon emission forecast data and generate a trend chart of carbon emissions. Analyze the changing characteristics of carbon emission forecast data, such as seasonal changes, extract its long-term trend, and determine the current carbon emission level. According to national and regional emission reduction targets, corporate social responsibility, and technical feasibility, set specific carbon emission reduction targets, which may include improving construction technology, purchasing energy-saving equipment, optimizing energy management, etc. Dynamic time series analysis is a statistical method used to analyze and predict time series data. Through dynamic time series analysis, energy consumption during subway construction can be more accurately predicted, specific carbon emission reduction targets can be set, and data support can be provided for carbon emission reduction.

[0018] Step 2: Plan based on the carbon emission reduction target and the energy consumption forecast data set to formulate multiple carbon emission reduction management plans.

[0019] Specifically, according to the specific carbon reduction targets set, combined with the energy consumption forecast data set, we can understand which links have high energy consumption and whether these links can reduce energy consumption through technical transformation or management optimization, and then make plans and plans. For example, we can analyze the energy consumption data in subway construction, understand which stages have high energy consumption, and then formulate corresponding transformation or optimization plans, such as improving energy efficiency, using renewable energy, optimizing building design and construction methods, etc. Consider different technical measures, management strategies, etc. to achieve carbon reduction targets, and generate multiple carbon reduction management plans for different stages.

[0020] For the energy optimization scheme of construction equipment, the energy consumption proportion of various types of equipment in different construction stages is analyzed according to the energy consumption prediction data set. For example, for high-energy-consuming equipment (such as shield machines), equipment with high energy efficiency ratings is preferred when purchasing or leasing; or a centralized management system for construction equipment is established to monitor the use time and operating status of the equipment in real time, and reasonably arrange the use of equipment according to the construction progress to avoid equipment idleness and idling; explore the use of battery power or hybrid power on some small construction equipment (such as small cranes, electric welders, etc.). If the energy consumption prediction data set shows that the power supply of these equipment at the construction site is more convenient, electric equipment can be gradually promoted. For the energy optimization scheme for material transportation, the energy consumption distribution of material transportation is analyzed according to the energy consumption prediction data set, and the optimal transportation route is planned in combination with the geographical location of the construction site and the material supply site. At the same time, the material demand during the construction process is accurately calculated to avoid multiple transportation due to excessive material inventory. According to the energy consumption prediction data set, the procurement and inventory cycle of materials are reasonably arranged. Similarly, for each other stage, the corresponding carbon emission reduction management plan is formulated through energy consumption prediction data and combined with carbon emission reduction targets. By combining carbon reduction targets and energy consumption forecast data, a variety of management plans are generated, providing multiple possible emission reduction paths and increasing the flexibility and adaptability of the plans.

[0021] Step three: Execute the multiple carbon emission reduction management schemes to perform carbon emission simulation analysis and generate multiple simulation analysis results, wherein the multiple simulation analysis results correspond to the multiple carbon emission reduction management schemes.

[0022] Specifically, simulate the formulated carbon emission reduction management plans and implement them. Build a model, set specific simulation scenarios for each carbon emission reduction management plan, input the relevant parameters and data of each emission reduction plan into the model, and simulate the energy consumption and carbon emissions of different plans under the set scenarios. Based on simulation analysis, including comprehensive consideration of energy consumption, emission sources and emission reduction measures, generate multiple analysis results to evaluate the impact of different carbon emission reduction management plans on reducing carbon emissions after implementation. Each carbon emission reduction management plan will have a corresponding simulation analysis result to show its emission reduction effect. Compare the results of different plans and identify the advantages and limitations of each plan. A comprehensive evaluation of different carbon emission reduction management plans is achieved, thereby providing an important reference for selecting the most effective emission reduction strategy, ensuring that the final selected management plan not only meets the emission reduction target, but also achieves the best results in actual operation.

[0023] Step 4: Perform carbon emission evaluation on the multiple simulation analysis results based on the carbon emission reduction target, traverse the multiple carbon emission reduction management solutions for screening according to the evaluation results, and determine a first carbon emission management solution.

[0024] Specifically, the Euclidean distance between each simulation analysis result and the carbon emission reduction target is calculated in turn to obtain multiple distance values, and the simulation analysis results are marked according to different distance values. The smaller the distance, the closer the simulation analysis result is to the target. A preset threshold is set, and the simulation analysis results corresponding to the distance value greater than the preset threshold are marked for carbon emission reduction. Carbon emissions are evaluated for each simulation analysis result according to the mark. Weights are assigned to the evaluation results, and the carbon emission reduction management plan with the best current effect is selected as the first carbon emission management plan. The first carbon emission management plan is obtained through screening, ensuring that the selected plan can most effectively achieve the carbon emission reduction target.

[0025] Step 5: Build a full life cycle carbon emission data monitoring platform, execute the first carbon emission management plan for real-time data collection, and generate a real-time carbon emission data set.

[0026] Specifically, a full-life cycle carbon emission data monitoring platform is built, including the data collection layer, communication network layer, data analysis layer and data output layer. Each layer undertakes different functions, such as data collection, transmission, analysis and display. According to the previously selected optimal carbon emission reduction management plan, specific emission reduction measures are implemented. Through the data collection layer and IoT devices, real-time monitoring of each key link of subway construction is carried out. The data is transmitted to the cloud server through the communication network layer for storage, and the stored data is synchronized to the data analysis layer for integration and analysis to obtain a data set, including emission, time, location and other information. Finally, the real-time carbon emission data set is output through the data output layer. Through real-time monitoring and feedback, the carbon emission management plan can be fully and accurately monitored and analyzed, thereby providing strong data support for carbon emission reduction management.

[0027] Step six: Tracking is performed according to the real-time carbon emission data set, dynamically adjusting the first carbon emission management plan according to the tracking feedback data set, and performing intelligent carbon emission reduction management for subway construction according to the adjustment results.

[0028] Specifically, monitoring and tracing are carried out based on the real-time carbon emission data set, multiple carbon emission monitoring points are determined, and each monitoring point is tracked to obtain the trajectory to obtain the tracking feedback data set. The tracking feedback data set is analyzed to identify the deficiencies and problems in the management plan. According to the analysis results, the first carbon emission management plan is adjusted and optimized, including changing the construction method, adjusting the energy use strategy, improving material selection, etc. The adjusted management plan is applied to the actual operation of subway construction, and the precise control of the carbon emission reduction process is achieved through intelligent management means, including real-time monitoring, early warning system, automatic adjustment and other intelligent functions. Continuously collect and analyze real-time carbon emission data, continuously optimize the carbon emission management plan, realize the intelligent and dynamic carbon emission reduction management, and improve management efficiency and environmental adaptability.

[0029] Furthermore, step one of this application includes:

[0030] Retrieve historical energy consumption information of subway construction and operation, trace the source according to the historical energy consumption information, and determine multiple energy consumption sources; divide the multiple energy consumption sources according to the time series of subway construction and operation, and generate multiple energy consumption division lists; build a dynamic time series analysis model based on the LSTM neural network; synchronize the multiple energy consumption division lists to the dynamic time series analysis model for predictive calculation, and obtain the energy consumption prediction data set of subway construction and operation.

[0031] Specifically, extract historical energy consumption information from the database or relevant records of the subway construction project, including electricity consumption, fuel use records, water resource consumption, etc. Ensure that the collected data covers the entire construction cycle, from project start to completion. Classify the collected energy consumption data according to different energy types, such as electricity, fuel oil, natural gas, water, etc. Divide the subway construction project into different stages, such as preliminary preparation, civil engineering, equipment installation, decoration, etc., and identify the specific activities that consume energy in each stage. For example, energy consumption in preliminary preparation includes electricity and IT equipment used in office design drawings, etc.; energy consumption in the civil engineering stage may include excavation equipment, concrete mixing, material transportation, temporary lighting, etc.; energy consumption in the equipment installation stage may involve the installation and testing of elevators, escalators, ventilation systems, etc. Associate historical energy consumption data with specific equipment or processes. For example, during the construction stage, the energy consumption source may be mainly fuel consumption of construction equipment (such as cranes, excavators, etc.). Multiple energy consumption sources are sorted and divided according to their chronological order during the construction and operation of the subway, and each energy consumption source is associated with its specific stage or time point in the construction process. They are divided according to the specific stage to obtain multiple energy consumption division lists, each list containing energy consumption sources within a specific stage.

[0032] Dynamic time series analysis is a statistical method used to analyze and predict time series data. LSTM is a special recurrent neural network (RNN) that can learn long-term dependencies through its unique network structure. In time series analysis, LSTM can capture long-term trends and patterns in data. Designing the structure of the LSTM neural network includes determining the number of layers of the network, the number of neurons in each layer, the activation function, etc. At the same time, it is necessary to decide whether to use bidirectional LSTM or other variants to improve the performance of the model. The LSTM model is trained using the prepared historical energy consumption information. During the training process, the parameters of the model, such as learning rate, batch size, etc., need to be adjusted to optimize the performance of the model. Multiple energy consumption partition lists are used as inputs to the LSTM network and input into the dynamic time series analysis model that has been constructed. The energy consumption of subway construction in the future period is obtained through prediction calculation, that is, the energy consumption prediction dataset. Accurately predicting the energy consumption of subway construction in the future period through the LSTM neural network will help set accurate carbon reduction targets.

[0033] Furthermore, the present application also includes the following steps:

[0034] Retrieve historical data on carbon emission influencing factors to calculate and obtain a carbon emission coefficient; make a prediction based on the energy consumption prediction data set in combination with the carbon emission coefficient to obtain carbon emission prediction data; model the carbon emission prediction data based on a time series analysis algorithm in combination with the energy consumption prediction data set to generate a carbon emission trend; identify the changing characteristics of the carbon emission prediction data and extract the long-term trend of the carbon emission trend; set the carbon emission reduction target based on the long-term trend in combination with the changing characteristics.

[0035] Specifically, collect and retrieve historical carbon emission data and various influencing factor data related to it, including energy consumption, production efficiency, carbon emission factors of different energy sources, production activity data, etc. Analyze the collected historical data in detail to determine which factors have a significant impact on carbon emissions and the quantitative relationship between these factors and carbon emissions. Based on the results of data analysis, calculate one or more carbon emission coefficients to reflect the degree of influence of different factors on carbon emissions. Use dynamic time series analysis to obtain an energy consumption forecast data set, which contains the forecast value of energy consumption in the future. Consider the carbon emission coefficient, that is, the carbon emissions generated per unit of energy consumption, and multiply the predicted value of energy consumption by the corresponding carbon emission coefficient to estimate future carbon emissions and obtain carbon emission forecast data.

[0036] Based on time series analysis algorithms, such as ARIMA, seasonal decomposition, etc., combined with energy consumption forecast data sets, the carbon emission forecast quantity is modeled, and algorithms are used to analyze data to reveal the long-term trend and pattern of carbon emissions, and generate corresponding trend graphs or models. Unlike dynamic timing analysis algorithms, dynamic timing analysis focuses more on timing verification of digital circuit design and can handle more complex time series data, such as nonlinear relationships and long-term dependencies, while time series analysis is a broader statistical method used to analyze and predict data sequences that change over time, and is usually applicable to simpler time series data. Analyze the carbon emission forecast data to identify its change characteristics, including data volatility, seasonality, and periodicity. Based on the analysis of change characteristics, extract the long-term trend of carbon emission trends and identify the overall direction and pattern of carbon emissions over time. Set specific carbon emission reduction targets based on the extracted long-term trends and change characteristics. For example, if it is found that the carbon emissions of a city are on an upward trend in the next few years and have obvious seasonal characteristics, set a goal to reduce carbon emissions by 10% in the next few years and formulate corresponding emission reduction measures based on seasonal characteristics. By combining energy consumption forecasts and carbon emission coefficients, future carbon emissions can be accurately predicted, providing data support for carbon emission reduction.

[0037] Further, as attached Figure 2 As shown, step 4 of this application includes:

[0038] The Euclidean distances between the multiple simulation analysis results and the carbon emission reduction target are calculated in sequence to obtain multiple distance values, wherein the multiple distance values ​​correspond to the multiple simulation analysis results; the multiple simulation analysis results are labeled according to the multiple distance values ​​to generate multiple carbon emission reduction labels; carbon emission evaluation is performed on the multiple simulation analysis results according to the multiple carbon emission reduction labels to obtain evaluation results; weights are assigned to the evaluation results, and the multiple carbon emission reduction management schemes are arranged in descending order according to the weight assignment results, and the first-ranked carbon emission reduction management scheme is selected as the first carbon emission management scheme.

[0039] Specifically, the Euclidean distance between each simulation analysis result and the set carbon reduction target is calculated. Euclidean distance is a mathematical method for measuring the distance between two points. It is used here to measure the gap between the carbon emissions of each solution and the target. Through calculation, multiple distance values ​​are obtained to reflect the gap between each solution and the emission reduction target. Each distance value corresponds to a specific simulation analysis result, so that the gap between each solution and the emission reduction target can be clearly seen. According to the specific requirements of the emission reduction target, industry standards, technical feasibility, etc., a preset threshold is set to provide a clear boundary to quickly identify which simulation analysis results are effective and which need further improvement. The smaller the distance, the closer the simulation analysis result is to the target. The simulation analysis result with a distance value greater than the preset threshold is marked with a specific carbon reduction mark, which means that the gap between the result and the target is large and needs further optimization or adjustment. The mark can be a simple color coding, star rating or any other method that can intuitively represent the gap.

[0040] Based on the generated identification, each simulation analysis result is evaluated, including consideration of emission reduction effect, cost-effectiveness and feasibility of implementation. The evaluation results are weighted, and different factors are assigned different weights based on their importance in the evaluation results. For example, a 50% weight is assigned to the distance value, a 30% weight is assigned to the economic cost, and a 20% weight is assigned to the implementation difficulty. Based on the weight allocation results, multiple carbon emission reduction management plans are arranged in descending order, and the higher the ranking, the better the performance in achieving carbon emission reduction goals. The plan ranked first from the descending order is selected as the first carbon emission management plan. This plan is considered to be the best among all plans.

[0041] In a specific example, the normalization factor is set to 5 million, the low difficulty is 0.1, the medium difficulty is 0.5, and the high difficulty is 0.9. Three schemes A, B, and C are given. The distance value of scheme A is 0.5, the economic cost is 10 million, and the implementation difficulty is medium; the distance value of scheme B is 0.3, the economic cost is 5 million, and the implementation difficulty is low; the distance value of scheme C is 0.7, the economic cost is 8 million, and the implementation difficulty is high. The calculation and evaluation results of these three schemes are: Scheme A = 0.5*50% + (1000 / 500)*30% + 0.5*20% = 0.25 + 0.6 + 0.1 = 0.95; Scheme B = 0.3*50% + (500 / 500)*30% + 0.1*20% = 0.15 + 0.3 + 0.02 = 0.47; Scheme C = 0.7*50% + (800 / 500)*30% + 0.9*20% = 0.35 + 0.48 + 0.18 = 1.01. Therefore, Scheme C is selected as the first carbon emission management scheme. By weight allocation, the decision-making process can be optimized, and the scheme ranked first can be selected as the first carbon emission management scheme, ensuring the consistency between the selected scheme and the carbon emission reduction target.

[0042] Furthermore, step five of this application includes:

[0043] The carbon emission data monitoring platform includes a data collection layer, a communication network layer, a data analysis layer, and a data output layer; the first carbon emission management plan is executed, and carbon emission is monitored at multiple carbon emission monitoring points through the data collection layer in combination with the Internet of Things equipment to obtain multiple carbon emission data blocks; the multiple carbon emission data blocks are transmitted to the cloud server through the communication network layer for storage according to the collection sequence, and the stored data is synchronized to the data analysis layer for integration and analysis to generate a real-time carbon emission data set; the real-time carbon emission data set is output through the data output layer.

[0044] Specifically, a full-life cycle carbon emission data monitoring platform is built, which includes a data collection layer, a communication network layer, a data analysis layer, and a data output layer. The data collection layer is the basic layer of the platform, responsible for real-time collection of various data related to carbon emissions. Data sources include energy consumption data, production process data, transportation data, etc. The communication network layer is responsible for transmitting the collected data to the data analysis layer, including wired or wireless communication networks. The data analysis layer is the core layer of the platform, responsible for processing, analyzing and modeling the collected data. The data output layer is responsible for outputting the analysis results in the form of visualization or reports so that users can easily understand and use this information, including charts, dashboards, reports, etc.

[0045] Execute the optimal carbon emission reduction management plan, use the data collection layer to collect data from each carbon emission monitoring point, and use IoT devices such as sensors and smart meters to automatically and real-time monitor carbon emissions. Perform real-time monitoring of multiple carbon emission monitoring points and collect carbon emission data. The data collected at each monitoring point forms a data block, which contains detailed information about carbon emissions, such as emissions, time, and location. Through the communication network layer, multiple carbon emission data blocks are transmitted from the data collection layer to the cloud server. After the data arrives at the cloud server, it is stored according to the collection sequence to maintain the integrity and traceability of the data. The data stored on the cloud server is synchronized to the data analysis layer, and the data is integrated and analyzed, including data cleaning module, data integration module and data analysis module, which can automatically process and analyze carbon emission data and generate real-time carbon emission data sets. Through the data output layer, the real-time carbon emission data set is output in a visual form, including charts, reports, real-time monitoring interfaces, etc. Through the full life cycle carbon emission data monitoring platform, the optimal carbon emission management plan is processed to obtain a real-time carbon emission data set, ensuring that decision makers can obtain accurate carbon emission data in a timely manner, thereby effectively managing carbon emission reduction work.

[0046] Furthermore, step six of this application includes:

[0047] Based on the real-time carbon emission data set, monitoring and tracing are performed to determine the multiple carbon emission monitoring points; carbon footprint tracking is performed according to the multiple carbon emission monitoring points to obtain a carbon emission trajectory; and the carbon emission trajectory is added to the tracking feedback data set.

[0048] Specifically, using the real-time carbon emission data set, the monitoring points are traced for analysis, and time series analysis and spatial analysis are performed to determine the source and path of carbon emissions at each monitoring point. Through monitoring and tracing, it is possible to determine which monitoring points are the main sources of carbon emissions and which monitoring points have a greater impact on total emissions. Carbon footprint tracking is performed based on the multiple carbon emission monitoring points previously determined. Carbon footprint tracking involves tracking the source, flow and final destination of carbon emissions to understand the dynamic changes in carbon emissions. Through carbon footprint tracking, the carbon emission trajectory of each monitoring point can be obtained, reflecting the changes in carbon emissions over time and space. The obtained carbon emission trajectory is added to the tracking feedback data set. The tracking feedback data set is a comprehensive data set that contains information such as carbon emission monitoring, tracing, and tracking. Through carbon footprint tracking and the acquisition of carbon emission trajectories, we can gain an in-depth understanding of the dynamic changes in carbon emissions, which helps to adjust and optimize emission reduction strategies in a timely manner.

[0049] Furthermore, the present application also includes the following steps:

[0050] A data integrity verification channel is established, and the data integrity of the tracking feedback data set is verified through the integrity verification channel to generate a data verification result; incomplete data in the tracking feedback data set is eliminated according to the verification result to generate multiple complete tracking feedback data; similarity clustering analysis is performed on the multiple complete tracking feedback data to generate data similarity clustering results; feature anomaly evaluation is performed according to the data similarity clustering results to generate feature anomaly evaluation results; abnormal data is eliminated on the data similarity clustering results according to the feature anomaly evaluation results, and the tracking feedback data set is updated.

[0051] Specifically, a data integrity verification channel is established to verify the data in the tracking feedback data set, including checking the consistency, completeness, accuracy and timeliness of the data. During the verification process, data verification results are generated, reflecting the integrity status of the data set, including possible problems and errors. According to the verification results, incomplete data in the tracking feedback data set are eliminated, such as deleting erroneous data, correcting inaccurate data, or filling in missing data. By eliminating incomplete data, multiple complete tracking feedback data are generated. These data sets contain accurate data that have been verified and cleaned, which can be used to formulate and optimize carbon emission reduction strategies. Through similarity clustering analysis, similarity analysis is performed on multiple data sets, and data points or data sets with similar characteristics are classified into one category, thereby revealing the inherent patterns and structures in the data. Through similarity clustering analysis, data similarity clustering results are generated, which reflect the similar patterns and structures in the data set, which helps to identify different types of carbon emission behaviors or patterns.

[0052] Based on the clustering results, the features in each cluster are evaluated for abnormalities, and the data is checked for outliers, irregular patterns, or behaviors that do not meet expected characteristics. Through feature anomaly evaluation, an evaluation result is generated, which reflects the abnormal features in the data, including their location, type, and potential causes. According to the feature anomaly evaluation results, abnormal data is removed for data similarity clustering results to complete data filtering. By removing abnormal data, the tracking feedback data set is updated. The updated data set contains accurate data that has been cleaned and verified, which can be used for more accurate and effective carbon reduction strategy formulation and optimization. Incomplete data and abnormal data in the tracking feedback data set are removed to improve the quality and reliability of the data set.

[0053] Furthermore, the present application also includes the following steps:

[0054] Performing data linear fitting according to the data similarity clustering result to generate a fitting result; performing data deviation evaluation on the multiple complete tracking feedback data in the data similarity clustering result according to the fitting result to generate multiple data deviation values; and generating the feature anomaly evaluation result according to the multiple data deviation values.

[0055] Specifically, similar clustering analysis is performed on multiple complete tracking feedback data to obtain data similar clustering results, and a suitable linear fitting model (such as the least squares method) is selected to fit the data similar clustering results. Linear fitting is a statistical method used to discover linear relationships and trends in data sets. Based on the linear fitting results, a deviation evaluation is performed on each data point to evaluate the degree of deviation of each data point from the overall trend. Deviation evaluation involves calculating the difference between each data point and the fitting curve, that is, the data deviation value. Through data deviation evaluation, multiple data deviation values ​​are generated. These values ​​reflect the difference between each data point and the fitting curve, which helps to identify anomalies or deviations in the data. Based on multiple data deviation values, the features are evaluated for abnormality, and feature abnormality evaluation results are generated, including identified abnormal data points, inconsistencies in data distribution, etc. Through data deviation values, abnormal features in the data can be discovered in a timely manner, which helps to understand abnormal patterns and potential problems in the data set.

[0056] In summary, the carbon emission reduction management method for subway construction under dynamic time sequence provided by this application has the following technical effects:

[0057] By using dynamic time series analysis to calculate the energy consumption forecast data set of subway construction and operation, the carbon emission reduction target is set according to the energy consumption forecast data set; based on the carbon emission reduction target and the energy consumption forecast data, planning is carried out to formulate multiple carbon emission reduction management plans; the multiple carbon emission reduction management plans are executed to perform carbon emission simulation analysis to generate multiple simulation analysis results, and the multiple simulation analysis results correspond to the multiple carbon emission reduction management plans; based on the carbon emission reduction target, the multiple simulation analysis results are evaluated for carbon emission, and the multiple carbon emission reduction management plans are traversed according to the evaluation results to screen and determine the first carbon emission management plan; a full life cycle carbon emission data monitoring platform is built, the first carbon emission management plan is executed for real-time collection to generate a real-time carbon emission data set; tracking is carried out according to the real-time carbon emission data set, the first carbon emission management plan is dynamically adjusted according to the tracking feedback data set, and intelligent carbon emission reduction management is carried out for subway construction according to the adjustment results. In other words, by using dynamic time series analysis, the carbon emission reduction at different stages of the subway construction process is finely managed, multiple management plans are formulated and simulated and analyzed, and the best emission reduction strategy is determined, so as to achieve more efficient carbon emission reduction management and improve energy utilization efficiency.

[0058] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for managing carbon emission reduction in subway construction under dynamic time sequence, characterized in that: include: Calculate the energy consumption prediction data set of subway construction and operation by using dynamic time series analysis, and set carbon emission reduction targets according to the energy consumption prediction data set; Based on the carbon emission reduction target and the energy consumption forecast data set, a plurality of carbon emission reduction management plans are formulated; Executing the multiple carbon emission reduction management schemes to perform carbon emission simulation analysis and generate multiple simulation analysis results, wherein the multiple simulation analysis results correspond to the multiple carbon emission reduction management schemes; Performing a carbon emission assessment on the multiple simulation analysis results based on the carbon emission reduction target, traversing the multiple carbon emission reduction management solutions for screening according to the assessment results, and determining a first carbon emission management solution; Build a full life cycle carbon emission data monitoring platform, implement the first carbon emission management solution for real-time data collection, and generate a real-time carbon emission data set; Tracking is performed according to the real-time carbon emission data set, the first carbon emission management plan is dynamically adjusted according to the tracking feedback data set, and intelligent carbon emission reduction management is performed on subway construction according to the adjustment results.

2. A method for managing carbon emission reduction in subway construction under dynamic time sequence as claimed in claim 1, characterized in that: The energy consumption forecast data set for subway construction and operation is calculated using dynamic time series analysis, including: Retrieve historical energy consumption information of subway construction and operation, trace the source according to the historical energy consumption information, and identify multiple energy consumption sources; Dividing the multiple energy consumption sources according to the time sequence of subway construction and operation to generate multiple energy consumption division lists; Build a dynamic time series analysis model based on LSTM neural network; The multiple energy consumption division lists are synchronized to the dynamic time series analysis model for prediction calculation to obtain the energy consumption prediction data set for subway construction and operation.

3. The method for managing carbon emission reduction in subway construction under dynamic time sequence as claimed in claim 1, characterized in that: Setting a carbon reduction target based on the energy consumption forecast data set includes: Retrieve historical carbon emission influencing factor data to calculate and obtain the carbon emission coefficient; Perform prediction based on the energy consumption prediction data set combined with the carbon emission coefficient to obtain carbon emission prediction data; Modeling the carbon emission prediction data based on a time series analysis algorithm combined with the energy consumption prediction data set to generate a carbon emission trend; Identify the change characteristics of the carbon emission forecast data and extract the long-term trend of the carbon emission trend; The carbon emission reduction target is set according to the long-term trend and the changing characteristics.

4. The method for managing carbon emission reduction in subway construction under dynamic time sequence as claimed in claim 1, characterized in that: Performing a carbon emission assessment on the multiple simulation analysis results based on the carbon emission reduction target, traversing the multiple carbon emission reduction management solutions for screening according to the assessment results, and determining a first carbon emission management solution, including: sequentially calculating the Euclidean distances between the plurality of simulation analysis results and the carbon emission reduction target to obtain a plurality of distance values, wherein the plurality of distance values ​​correspond to the plurality of simulation analysis results; Labeling the multiple simulation analysis results according to the multiple distance values ​​to generate multiple carbon emission reduction labels; Performing carbon emission assessment on the multiple simulation analysis results according to the multiple carbon emission reduction identifiers to obtain an assessment result; The evaluation results are weighted, the multiple carbon emission reduction management schemes are arranged in descending order according to the weighted allocation results, and the first-ranked carbon emission reduction management scheme is selected as the first carbon emission management scheme.

5. The method for managing carbon emission reduction in subway construction under dynamic time sequence as claimed in claim 1, characterized in that: Build a full life cycle carbon emission data monitoring platform, implement the first carbon emission management solution for real-time collection, and generate a real-time carbon emission data set, including: The carbon emission data monitoring platform includes a data collection layer, a communication network layer, a data analysis layer, and a data output layer; Execute the first carbon emission management solution, monitor carbon emissions at multiple carbon emission monitoring points through the data collection layer in combination with the Internet of Things device, and obtain multiple carbon emission data blocks; Transmitting the plurality of carbon emission data blocks to the cloud server through the communication network layer for storage according to the collection time sequence, and synchronizing the stored data to the data analysis layer for integration and analysis to generate a real-time carbon emission data set; The real-time carbon emission data set is output through the data output layer.

6. A method for managing carbon emission reduction in subway construction under dynamic time sequence as claimed in claim 5, characterized in that: Tracking based on the real-time carbon emissions dataset includes: Perform monitoring and tracing based on the real-time carbon emission data set to determine the multiple carbon emission monitoring points; Tracking carbon footprints according to the multiple carbon emission monitoring points to obtain a carbon emission trajectory; Add the carbon emission trajectory to the tracking feedback dataset.

7. The method for managing carbon emission reduction in subway construction under dynamic time sequence as claimed in claim 1, characterized in that: include: Establishing a data integrity verification channel, verifying the data integrity of the tracking feedback data set through the integrity verification channel, and generating a data verification result; Eliminate incomplete data in the tracking feedback data set according to the verification result to generate multiple complete tracking feedback data; Performing similarity clustering analysis on the multiple complete tracking feedback data to generate data similarity clustering results; Perform feature anomaly evaluation based on the data similarity clustering results to generate feature anomaly evaluation results; Abnormal data is eliminated from the data similarity clustering result according to the feature abnormality evaluation result, and the tracking feedback data set is updated.

8. A method for managing carbon emission reduction in subway construction under dynamic time sequence as claimed in claim 7, characterized in that: include: Performing data linear fitting according to the data similarity clustering results to generate fitting results; Performing data deviation evaluation on the plurality of complete tracking feedback data in the data similarity clustering result according to the fitting result to generate a plurality of data deviation values; The feature abnormality evaluation result is generated according to the multiple data deviation values.

Images