Railway traffic engineering carbon emission evaluation system and method based on full life cycle

Abstract

The invention relates to the field of carbon emission measurement and calculation, and particularly discloses a railway traffic engineering carbon emission evaluation system and method based on a full life cycle. Carbon emission accounting with day as a unit is carried out on field construction data by using an artificial intelligence technology based on deep learning, and then multi-time-domain-scale-based time sequence analysis is carried out on carbon emission data generated by engineering construction, so that the regularity and tendency characteristics of carbon emission change are mined; therefore, the total carbon emission of the whole life cycle of the railway traffic engineering is intelligently estimated on the basis, and whether a carbon emission standard exceeding early warning prompt is generated or not is determined by combining the expected total carbon emission, so that real-time monitoring and intelligent early warning of the carbon emission of the railway traffic engineering can be realized, measures can be taken in advance, engineering design is optimized, and the economic benefit is improved. Carbon emission is reduced, and green and low-carbon railway traffic engineering is realized.

Description

Technical Field

[0001] The present application relates to the field of carbon emission measurement, and more specifically, to a carbon emission evaluation system and method for railway transportation projects based on the entire life cycle. Background Art

[0002] Carbon emission measurement is an assessment activity used to quantify the amount of carbon dioxide emitted directly or indirectly into the atmosphere by a specific entity (such as an organization, facility or product) over a certain period of time. This process involves detailed recording and calculation of activities such as energy consumption, material use, production processes and waste disposal. The purpose of carbon emission measurement is to measure the potential impact on climate change, provide a scientific basis for emission reduction strategies, and support companies and individuals to make more informed decisions in addressing climate change.

[0003] As global climate change intensifies, reducing carbon emissions has become an important issue of common concern to the international community. As a key component of the modern transportation system, railway transportation, while promoting economic development, also faces major challenges in energy conservation and emission reduction. The entire life cycle of a railway construction project includes planning, design, construction, operation and maintenance, and each stage will produce varying degrees of carbon emissions. Therefore, accurate carbon emission evaluation of railway transportation engineering projects is of great significance to achieving green and low-carbon development.

[0004] Traditionally, the carbon emission assessment of railway transportation projects often relies on the summary report after the project is completed. For example, the Chinese patent with application number 202410059358.5 discloses a method and system for calculating and analyzing carbon emissions of transportation engineering construction projects, including: collecting basic parameters of transportation engineering construction projects; identifying and extracting PDF files of transportation engineering construction project budgets to obtain basic data on the amount of manpower, machinery, and materials for carbon emission calculations; calculating the carbon emissions corresponding to manpower, machinery, and materials for each sub-project by the carbon emission factor method, and summarizing and calculating the total carbon emissions; using multidimensional data visualization technology to statistically analyze the calculation results of transportation engineering carbon emissions to obtain the carbon emission distribution characteristics of transportation engineering construction projects; and preparing and exporting a PDF report on carbon emission analysis of transportation engineering construction projects. This method is not only lagging behind, but also difficult to accurately reflect the actual carbon emissions at each stage of the project, and lacks effective guidance for timely emission reduction measures and optimization of engineering design.

[0005] Therefore, there is a need for an optimized carbon emission evaluation system and method for railway transportation projects based on the entire life cycle. Summary of the invention

[0006] In order to solve the above technical problems, this application is proposed. The embodiment of the present application provides a railway transportation project carbon emission evaluation system and method based on the whole life cycle, which uses a sensor group to collect the on-site construction data of the railway transportation project, and uses artificial intelligence technology based on deep learning to calculate the carbon emissions of the on-site construction data in units of days, and then conducts a time series analysis based on multiple time domain scales on the carbon emission data generated by the construction of the project to dig out the regularity and trend characteristics of the carbon emission changes, so as to intelligently estimate the total carbon emissions of the railway transportation project in the whole life cycle on this basis, and then combine the expected total carbon emissions to determine whether to generate a warning prompt for the carbon emissions exceeding the standard, which can realize real-time monitoring and intelligent early warning of carbon emissions of railway transportation projects, and help take measures in advance, optimize engineering design, reduce carbon emissions, and realize green and low-carbon railway transportation projects.

[0007] Accordingly, according to one aspect of the present application, a railway transportation engineering carbon emission evaluation system based on the entire life cycle is provided, which includes: A construction data collection module, used to collect on-site construction data of the railway transportation project using a sensor group to obtain a collection of on-site construction data; A carbon emission accounting module, used for performing daily carbon emission accounting based on the set of on-site construction data to obtain a daily time queue of carbon emissions; A time series coding module, used for performing time series coding on the day-level time queue of the carbon emissions based on singular spectrum decomposition to obtain a plurality of carbon emissions time series coding feature vectors; A feature dynamic optimization aggregation module is used to perform feature dynamic optimization aggregation on the multiple carbon emission time series coding feature vectors to obtain a carbon emission multi-time domain scale significant aggregation coding vector; The early warning prompt generation module is used to determine whether to generate an early warning prompt of carbon emissions exceeding the standard based on the multi-temporal scale significant aggregation coding vector of carbon emissions.

[0008] Specifically, the carbon emission accounting module includes: A data segmentation unit, used for segmenting the set of on-site construction data by day to obtain a set of on-site construction data at the day level; The construction data carbon accounting unit is used to input each daily on-site construction data in the set of daily on-site construction data into the carbon emission accounting model to obtain the daily time queue of the carbon emission.

[0009] Specifically, the timing coding module includes: A sequence decoding unit, used for inputting the day-level time queue of carbon emissions into a sequence decoder based on singular spectrum decomposition to obtain a plurality of carbon emissions time series subsequences; The sequence encoding unit is used to input the multiple carbon emission time series subsequences into the sequence encoder based on the LSTM model respectively to obtain the multiple carbon emission time series encoding feature vectors.

[0010] Specifically, the feature dynamic optimization aggregation module includes: A pseudo-anchor aggregation center calculation unit, used to calculate a pseudo-anchor aggregation center representation vector of multiple time-domain features of carbon emissions based on the characteristic static potential energy distribution of the multiple carbon emissions time-series encoding feature vectors; A dynamic aggregation unit is used to dynamically aggregate the multiple carbon emission time series coding feature vectors based on the aggregation movement direction of each carbon emission time series coding feature vector in the multiple carbon emission time series coding feature vectors relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain the carbon emission multi-time domain scale significant aggregation coding vector.

[0011] Specifically, the pseudo anchor aggregation center calculation unit is used to: Inputting each of the plurality of carbon emission time series encoding feature vectors into a characteristic static potential energy measurement network to obtain a plurality of carbon emission time series characteristic static potential energy measurement coefficients; Inputting the plurality of carbon emission time series characteristic static potential energy measurement coefficients into a characteristic energy level screening gating unit to obtain a plurality of carbon emission time series characteristic static potential energy weight factors; Based on the static potential weight factors of the multiple carbon emission time series features, a weighted sum of the multiple carbon emission time series encoding feature vectors is calculated to obtain the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector.

[0012] Specifically, the dynamic polymerization unit is used to: Calculating the aggregation movement direction of each carbon emission time series encoding feature vector in the multiple carbon emission time series encoding feature vectors relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain multiple carbon emission time series feature aggregation movement directions; Based on the aggregation movement directions of the multiple carbon emission time series features, the multiple carbon emission time series coding feature vectors are dynamically aggregated toward the carbon emission multi-temporal feature pseudo-anchor aggregation center representation vector to obtain the carbon emission multi-temporal scale significant aggregation coding vector.

[0013] Specifically, the carbon emission time series feature aggregation movement direction is the arccosine function value between the carbon emission time series encoding feature vector and the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector.

[0014] Specifically, the early warning prompt generation module includes: A total carbon emission estimation unit, used for inputting the carbon emission multi-time domain scale significant aggregation coding vector into a decoder-based total carbon emission prediction module to obtain an estimated value of total carbon emission of railway traffic engineering; The warning generation unit is used to determine whether to generate a warning prompt of the carbon emissions exceeding the standard based on the comparison between the estimated value of the total carbon emissions of the railway transportation project and the expected total carbon emissions.

[0015] According to another aspect of the present application, a method for evaluating carbon emissions of railway transportation projects based on the entire life cycle is provided, which includes: Using the sensor group to collect on-site construction data of the railway transportation project to obtain a collection of on-site construction data; Performing daily carbon emission accounting based on the set of on-site construction data to obtain a daily time queue of carbon emissions; Performing time series coding based on singular spectrum decomposition on the day-level time queue of the carbon emissions to obtain a plurality of carbon emissions time series coding feature vectors; Performing dynamic optimization aggregation on the multiple carbon emission time series coding feature vectors to obtain a carbon emission multi-time domain scale significant aggregation coding vector; Based on the multi-temporal scale significant aggregation coding vector of carbon emissions, it is determined whether to generate an early warning prompt of carbon emissions exceeding the standard.

[0016] This application has at least the following technical effects: Compared with the prior art, the railway transportation project carbon emission evaluation system and method based on the whole life cycle provided by the present application utilizes a sensor group to collect on-site construction data of the railway transportation project, and utilizes artificial intelligence technology based on deep learning to calculate the carbon emissions of the on-site construction data on a daily basis, and then conducts a time series analysis based on multiple time domain scales on the carbon emission data generated by the construction of the project to explore the regularity and trend characteristics of the changes in carbon emissions, and on this basis, intelligently estimates the total carbon emissions of the railway transportation project over its entire life cycle, and then combines the expected total carbon emissions to determine whether to generate an early warning prompt for carbon emissions that are expected to exceed the standard, which can realize real-time monitoring and intelligent early warning of carbon emissions of railway transportation projects, and help to take measures in advance, optimize project design, reduce carbon emissions, and realize green and low-carbon railway transportation projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0018] Figure 1 It is a block diagram of a railway transportation project carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application.

[0019] Figure 2 This is a data flow diagram of a railway transportation project carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application.

[0020] Figure 3 It is a block diagram of the carbon emission accounting module in the railway transportation project carbon emission evaluation system based on the whole life cycle according to the embodiment of the present application.

[0021] Figure 4 It is a block diagram of the timing coding module in the railway transportation engineering carbon emission evaluation system based on the whole life cycle according to the embodiment of the present application.

[0022] Figure 5 This is a block diagram of a feature dynamic optimization aggregation module in a railway transportation engineering carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application.

[0023] Figure 6 This is a block diagram of a warning prompt generation module in a railway transportation project carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application.

[0024] Figure 7 This is a flow chart of a method for evaluating carbon emissions of railway transportation projects based on the entire life cycle according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0026] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0027] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0028] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0029] It is worth noting that in this application, all actions to obtain data are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0030] In response to the problems described in the above background technology, the present application proposes a carbon emission evaluation system for railway transportation projects based on the entire life cycle, which uses a sensor group to collect on-site construction data of railway transportation projects, and uses deep learning-based artificial intelligence technology to calculate the carbon emissions of on-site construction data on a daily basis, and then conducts a time series analysis based on multiple time domain scales on the carbon emission data generated by the construction of the project to explore the regularity and trend characteristics of carbon emission changes, and on this basis, intelligently estimates the total carbon emissions of the railway transportation project over its entire life cycle, and then combines the expected total carbon emissions to determine whether to generate a warning prompt for carbon emissions exceeding the standard, which can realize real-time monitoring and intelligent early warning of carbon emissions of railway transportation projects, help to take measures in advance, optimize project design, reduce carbon emissions, and realize green and low-carbon railway transportation projects.

[0031] Figure 1 It is a block diagram of a railway transportation project carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of a railway transportation project carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the railway transportation project carbon emission evaluation system 100 based on the whole life cycle includes: a construction data acquisition module 110, which is used to use a sensor group to collect on-site construction data of the railway transportation project to obtain a set of on-site construction data; a carbon emission accounting module 120, which is used to perform daily carbon emission accounting based on the set of on-site construction data to obtain a daily time queue of carbon emissions; a time series coding module 130, which is used to perform time series coding based on singular spectrum decomposition on the daily time queue of carbon emissions to obtain multiple carbon emission time series coding feature vectors; a feature dynamic optimization aggregation module 140, which is used to perform feature dynamic optimization aggregation on the multiple carbon emission time series coding feature vectors to obtain a carbon emission multi-time domain scale significant aggregation coding vector; an early warning prompt generation module 150, which is used to determine whether to generate a carbon emission excess warning prompt based on the carbon emission multi-time domain scale significant aggregation coding vector.

[0032] In the above-mentioned railway transportation project carbon emission evaluation system based on the whole life cycle, the construction data collection module 110 is used to collect the on-site construction data of the railway transportation project using the sensor group to obtain a collection of on-site construction data. In a specific example of the present application, the on-site construction data includes but is not limited to information such as power consumption, fuel usage, activation time of mechanical equipment, load conditions, the amount of building materials such as concrete and steel used, the amount of waste generated, and the number of construction personnel.

[0033] In order to achieve an accurate assessment of carbon emissions from railway transportation projects, it is essential to build a comprehensive data collection system. The construction of this system first depends on the selection of appropriate sensors and their reasonable layout. In the selection of sensors, it is necessary to consider equipment that can monitor all activities that may generate carbon emissions, such as electricity meters and flow meters for monitoring electricity and fuel consumption, weight and volume sensors for recording the amount of building materials used, engine speed sensors and working time timers installed on construction machinery, and GPS tracking devices for tracking vehicle travel distance and routes. In addition, weather station sensors are used to monitor environmental conditions such as temperature, humidity and wind speed, and exhaust emission analyzers are used to evaluate emissions during waste treatment. These sensors must not only have high accuracy and reliability, but also ensure that the main operating areas of the entire construction site are covered, and the positions must be reasonably arranged according to the distance restrictions of data transmission to ensure effective signal transmission.

[0034] Based on the selected sensors, the next step is to build an efficient data acquisition system. The system includes various types of sensors and their supporting data acquisition modules at the front-end hardware layer. Each module is responsible for reading data from a specific sensor and sending it to the back-end server via wired or wireless means. The network communication layer uses industrial-grade wireless network technology or LAN connection to ensure that the data is stably and reliably transmitted to the data center. The back-end software layer establishes a database management system to store all collected data, develops a data analysis platform to process and analyze raw data, and creates a user interface for viewing real-time data and historical records. Such a system design enables the large amount of complex data generated from on-site construction to be effectively captured and managed, providing a solid foundation for subsequent carbon emissions assessments.

[0035] Data quality control measures are equally important to ensure the authenticity and accuracy of the collected data. Sensors are calibrated regularly to ensure that the measured values ​​are within the allowable error range, and verified by comparing the readings between different sensors or introducing a third-party independent testing agency. At the same time, a special anomaly detection algorithm is designed to identify and mark data points that deviate from the normal range to eliminate the impact of errors or abnormal situations; and dual or even multiple sensors are configured for important parameters. Once a sensor fails, other backup sensors can continue to work to ensure data continuity. These measures ensure the quality of the collected data and provide a reliable basis for subsequent analysis.

[0036] Considering that more and more sensitive information is stored digitally, data security and privacy protection are particularly important in the entire data collection process. Use SSL / TLS protocol to encrypt all data packets transmitted on the network to prevent man-in-the-middle attacks; strictly set access rights for users of different levels to allow only authorized personnel to access core data; and anonymize data involving personal identity or other private information before saving. These measures are designed to maintain the security and integrity of data and prevent unauthorized access and use.

[0037] In addition to the above, the implementation steps should also be planned in detail. First, the demand analysis and planning stage requires communication with the project team to clarify which links are most likely to cause carbon emissions and determine the targets that need to be monitored. Next, in the hardware procurement and installation stage, sensors and other necessary equipment of corresponding specifications are purchased according to demand, and on-site deployment is completed. Subsequently, the system debugging and optimization stage starts the preliminary data collection process, checks the working status of each component, and adjusts the parameters until the best performance is achieved. Finally, in the long-term operation and maintenance support stage, a full-time team is set up to be responsible for daily maintenance and technical support, promptly resolve possible problems, and maintain the continuous and stable operation of the system.

[0038] In summary, by carefully selecting suitable sensors, building a robust data collection architecture, implementing strict data quality management strategies, following standardized implementation processes, and specifically applying various types of sensors, sensor groups can be effectively used to collect on-site construction data in railway transportation engineering projects, thereby providing a solid data foundation for subsequent carbon emission assessments.

[0039] In the above-mentioned railway transportation engineering carbon emission evaluation system based on the whole life cycle, the carbon emission accounting module 120 is used to calculate the daily carbon emission amount based on the set of on-site construction data to obtain the daily time queue of carbon emission amount. Figure 3 FIG. 1 is a block diagram of a carbon emission accounting module in a railway transportation engineering carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application. Figure 3As shown, the carbon emission accounting module 120 includes: a data segmentation unit 121, used to segment the set of on-site construction data by day to obtain a set of day-level on-site construction data; a construction data carbon accounting unit 122, used to input each day-level on-site construction data in the set of day-level on-site construction data into the carbon emission accounting model to obtain a day-level time queue of the carbon emissions.

[0040] Specifically, the data segmentation unit 121 is used to segment the set of on-site construction data in units of days to obtain a set of daily on-site construction data. Among them, the present application takes into account that the construction activities of railway transportation projects usually have a certain periodicity and regularity, and its engineering operations are carried out in an orderly manner according to the established schedule. The daily construction conditions (such as the use of machinery and equipment, material transportation, etc.) will affect the carbon emissions of the day. Therefore, in order to better capture the cyclical characteristics of construction activities, the present application segments the set of on-site construction data in units of days to form a set of daily on-site construction data, so as to facilitate the calculation and vertical comparison of daily carbon emissions, and then realize the estimation of carbon emissions for the entire life cycle of railway transportation projects.

[0041] Specifically, the construction data carbon accounting unit 122 is used to input each daily-level on-site construction data in the set of daily-level on-site construction data into the carbon emission accounting model to obtain the daily time queue of the carbon emissions. Among them, the daily-level on-site construction data represents all activity records related to carbon emissions in a day, and is the basic data for carbon emission accounting. In order to achieve a quantitative assessment of the carbon emissions generated by daily construction activities, the present application further uses a carbon emission accounting model to perform carbon emission accounting on each daily-level on-site construction data in the set of daily-level on-site construction data, so as to obtain the corresponding daily carbon emission estimates. In a specific example of the present application, the carbon emission accounting model uses a multi-layer perceptron (MLP, Multi-Layer Perceptron) model to estimate carbon emissions. Specifically, the multi-layer perceptron model is a feedforward neural network, which includes at least three layers of neurons: an input layer, a hidden layer, and an output layer. In the carbon emissions accounting, the input layer receives daily on-site construction data, and the hidden layer learns the complex relationship between carbon emissions and construction activities through nonlinear transformation and feature extraction of the daily on-site construction data. Finally, the daily carbon emissions estimate is given through the output layer, thereby realizing the daily accounting of carbon emissions of railway transportation projects and obtaining a daily time queue of carbon emissions.

[0042] In the above-mentioned railway transportation engineering carbon emission evaluation system based on the whole life cycle, the time series coding module 130 is used to perform time series coding based on singular spectrum decomposition on the day-level time queue of the carbon emission to obtain multiple carbon emission time series coding feature vectors. Figure 4 FIG. 1 is a block diagram of a timing coding module in a railway transportation engineering carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application. Figure 4 As shown, the time series encoding module 130 includes: a sequence decoding unit 131, which is used to input the day-level time queue of the carbon emissions into a sequence decoder based on singular spectrum decomposition to obtain multiple carbon emission time series subsequences; a sequence encoding unit 132, which is used to input the multiple carbon emission time series subsequences into a sequence encoder based on an LSTM model respectively to obtain the multiple carbon emission time series encoding feature vectors.

[0043] Specifically, the sequence decoding unit 131 is used to input the day-level time queue of the carbon emissions into a sequence decoder based on singular spectrum decomposition to obtain multiple carbon emissions time series subsequences. Specifically, since the carbon emissions of railway transportation projects have multi-scale time series characteristics, they may include long-term change trends, periodic fluctuations, and short-term random fluctuations. Therefore, in order to more accurately capture the multi-scale time domain change characteristics of the carbon emissions of railway transportation projects, this application uses singular spectrum decomposition (SSA, Singular Spectrum Analysis) to process the day-level time queue of carbon emissions. By establishing a time series trajectory matrix of carbon emissions, singular value decomposition, singular vector grouping and time series reconstruction, the day-level time queue of carbon emissions is decomposed into several independent time series components to obtain multiple carbon emissions time series subsequences, so as to reveal the main change trends, periodic patterns and noise components in the original day-level time queue of carbon emissions, thereby providing a clearer data view for the subsequent analysis of the law of carbon emissions changes.

[0044] Specifically, the sequence encoding unit 132 is used to input the multiple carbon emission time series subsequences into the sequence encoder based on the LSTM model to obtain the multiple carbon emission time series encoding feature vectors. In order to further capture the characteristics of the carbon emission time series change pattern contained in each carbon emission time series subsequence, the present application adopts the LSTM (Long Short-Term Memory, long short-term memory network) model that performs well in time series processing tasks to perform time series encoding on each carbon emission time series subsequence, so as to mine the long-term dependency relationship in each carbon emission time series subsequence and obtain multiple carbon emission time series encoding feature vectors. Among them, the LSTM model is a special recursive neural network (RNN), which is particularly suitable for processing and predicting data with time series characteristics. LSTM effectively solves the long-term dependency problem in traditional RNN by introducing a gating mechanism, so that the model can maintain the memory ability of information over a long time interval. For the carbon emission assessment of railway transportation engineering projects, when the carbon emission time series subsequence is input into the LSTM model, the model processes the elements in the sequence time step by time step, and updates the internal memory cell state according to the state of the previous moment and the current input. As the sequence progresses, LSTM gradually accumulates an understanding of the carbon emission behavior pattern during that time period. Finally, at the end of each subsequence, LSTM outputs a hidden state vector of a fixed length as the time series encoding feature vector of the subsequence. These feature vectors condense the key information of the original time series data, retaining the dynamic change characteristics in the time dimension, and integrating the interaction relationship between different variables, providing strong data support for the subsequent analysis and prediction of the change law of carbon emissions.

[0045] In the above-mentioned railway transportation project carbon emission evaluation system based on the whole life cycle, the feature dynamic optimization aggregation module 140 is used to perform feature dynamic optimization aggregation on the multiple carbon emission time series coding feature vectors to obtain a carbon emission multi-time domain scale significant aggregation coding vector. Among them, the present application takes into account that the multiple carbon emission time series coding feature vectors respectively represent the carbon emission characteristics on different time scales (such as short-term fluctuations, medium-term trends and long-term changes, etc.). In order to more comprehensively understand the carbon emission behavior of railway transportation projects, the present application further performs feature aggregation processing on the multiple carbon emission time series coding feature vectors to integrate the multi-scale information of carbon emission time series changes. In particular, considering that for carbon emissions, there may be certain synergistic effects or causal relationships between each carbon emission time series subsequence. For example, some short-term fluctuations may accumulate into medium- and long-term trend changes. Therefore, in order to better understand the dynamic changes of carbon emissions of railway transportation projects, the present application proposes a feature dynamic optimization aggregation method, which uses the feature correlation pattern between each carbon emission time series coding feature vector to perform feature dynamic integration and realize an in-depth analysis of the law of carbon emission changes. Among them, Figure 5 FIG. 1 is a block diagram of a characteristic dynamic optimization aggregation module in a railway transportation engineering carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application. Figure 5 As shown, the feature dynamic optimization aggregation module 140 includes: a pseudo-anchor aggregation center calculation unit 141, which is used to calculate the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector based on the feature static potential energy distribution of the multiple carbon emission time series coding feature vectors; a dynamic aggregation unit 142, which is used to dynamically aggregate the multiple carbon emission time series coding feature vectors based on the aggregation movement direction of each carbon emission time series coding feature vector in the multiple carbon emission time series coding feature vectors relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain the carbon emission multi-time domain scale significant aggregation coding vector.

[0046] Specifically, the pseudo anchor aggregation center calculation unit 141 includes: inputting each of the multiple carbon emission time series encoding feature vectors into a feature static potential energy measurement network to obtain multiple carbon emission time series feature static potential energy measurement coefficients, which are expressed as follows: ; ; in, represents the multiple carbon emission time series encoding feature vectors, , , and respectively represent the first, second, and third of the multiple carbon emission time series encoding feature vectors and A carbon emission time series encoding feature vector, is the number of feature vectors in the plurality of carbon emission time series encoding feature vectors, Indicates the The first The eigenvalues ​​at the positions, and Respectively represent the The characteristic mean and characteristic variance of the carbon emission time series encoding feature vector, is the characteristic scale value of the carbon emission time series encoding characteristic vector, The said The static potential energy measurement coefficient of the time series encoding feature vector of carbon emissions.

[0047] Specifically, the potential energy level of each carbon emission time series encoding feature vector under static conditions is evaluated through a feature static potential energy measurement network to reveal the importance and influence of each carbon emission time series subsequence under the current global feature distribution, as well as the intrinsic connection between each carbon emission time series subsequence, thereby obtaining multiple carbon emission time series feature static potential energy measurement coefficients.

[0048] In a specific example of the present application, the pseudo anchor aggregation center calculation unit 141 further includes: inputting the multiple carbon emission time series feature static potential energy measurement coefficients into the feature energy level screening gating unit to obtain multiple carbon emission time series feature static potential energy weight factors, which are expressed as follows: ; ; in, Indicates Normalized carbon emission time series characteristic static potential energy measurement coefficient, represents the gated mask function, represents the gating threshold, Indicates The static potential energy weight factor of the carbon emission time series characteristics.

[0049] The static potential energy measurement coefficients of multiple carbon emission time series features obtained are gated and masked through the feature energy level screening gating unit to screen out the time domain features that contribute more to the overall time series change characteristics of carbon emissions, ensure that they have higher potential energy values, and assign them corresponding weight factors. At the same time, the time domain features with smaller contributions are suppressed to reduce the impact of noise and irrelevant information on the final carbon emission estimation and reduce the risk of overfitting.

[0050] In a specific example of the present application, the pseudo anchor aggregation center calculation unit 141 further includes: based on the static potential weight factors of the multiple carbon emission time series features, calculating the weighted sum of the multiple carbon emission time series encoding feature vectors to obtain the carbon emission multi-time domain feature pseudo anchor aggregation center representation vector, which is expressed by the formula: ; in, The pseudo-anchored aggregation center representation vector representing the multi-temporal features of carbon emissions.

[0051] Specifically, based on the obtained weight factors, the multiple carbon emission time series encoding feature vectors are weighted and aggregated to reveal the characteristic distribution trend center of each carbon emission time series subsequence, and generate a carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector. In this way, the overall change trend of carbon emissions can be accurately reflected, thereby providing effective guidance for the subsequent aggregation process of carbon emission multi-scale time domain features.

[0052] Specifically, the dynamic aggregation unit 142 includes: calculating the aggregation movement direction of each carbon emission time series coding feature vector in the multiple carbon emission time series coding feature vectors relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain multiple carbon emission time series feature aggregation movement directions. The carbon emission time series feature aggregation movement direction is the arc cosine function value between the carbon emission time series coding feature vector and the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector, which is expressed by the formula: ; in, represents the magnitude of a vector, is the arccosine function, Indicates the The carbon emission time series encoding feature vectors represent the aggregation movement direction of the vector relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center.

[0053] Specifically, by calculating the aggregation movement direction of each carbon emission time series encoding feature vector relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector, the change trend of each carbon emission time domain feature relative to the center point is quantified, revealing the dynamic relationship and evolution path of each carbon emission time series subsequence within the carbon emission time series feature space, so as to identify the relative relationship between features and group behavior patterns.

[0054] In a specific example of the present application, the dynamic aggregation unit 142 further includes: based on the aggregation movement direction of the multiple carbon emission time series features, the multiple carbon emission time series coding feature vectors are dynamically aggregated toward the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain the carbon emission multi-time domain scale significant aggregation coding vector, which is expressed by the formula: ; in, represents the sine function, and denote the weight matrix and bias term respectively, A coding vector representing the significant aggregation of carbon emissions at multiple temporal scales.

[0055] Specifically, based on the aggregation movement direction of each carbon emission time series encoding feature vector and the characteristic static potential energy measurement coefficient, each carbon emission time series encoding feature vector is dynamically aggregated toward the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain a carbon emission multi-time domain scale significant aggregation encoding vector, thereby realizing a dynamic representation of the time series change trend of carbon emissions of railway transportation engineering. In this way, not only the carbon emission characteristics at each time scale are considered, but also the interaction and influence between carbon emission characteristics at different time scales are further revealed through the feature dynamic optimization aggregation process, thereby deepening the understanding of the carbon emission behavior of railway transportation engineering.

[0056] In the above-mentioned railway transportation project carbon emission evaluation system based on the whole life cycle, the warning prompt generation module 150 is used to determine whether to generate a warning prompt of carbon emission exceeding the standard based on the multi-temporal scale significant aggregation coding vector of carbon emission. Figure 6 FIG. 1 is a block diagram of a warning prompt generation module in a railway transportation engineering carbon emission evaluation system based on the entire life cycle according to an embodiment of the present application. Figure 6 As shown, the early warning generation module 150 includes: a total carbon emission estimation unit 151, which is used to input the carbon emission multi-time domain scale significant aggregation coding vector into the decoder-based total carbon emission prediction module to obtain the total carbon emission estimation value of the railway traffic project; an early warning generation unit 152, which is used to determine whether to generate the carbon emission exceeding the standard early warning based on the comparison between the total carbon emission estimation value of the railway traffic project and the expected total carbon emissions.

[0057] Specifically, the total carbon emissions estimation unit 151 is used to input the carbon emissions multi-time domain scale significant aggregation coding vector into the total carbon emissions prediction module based on the decoder to obtain the total carbon emissions estimation value of the railway traffic project. In a specific example of the present application, the decoder adopts a deep neural network structure, which can effectively capture the dynamic characteristics of carbon emissions changing over time by learning the time series information in the carbon emissions multi-time domain scale significant aggregation coding vector, and decode and output the total carbon emissions estimation value of the railway traffic project accordingly, thereby realizing the intelligent estimation of the carbon emission level in the whole life cycle of the railway traffic project. In the technical solution of the present application, considering the complexity of the carbon emissions prediction task, the decoder usually adopts a multi-level structure. Each layer is responsible for restoring a part of the time series characteristics or details at a specific time scale. For example, the bottom layer may focus on capturing short-term fluctuations, while the upper layer is committed to restoring long-term trends. Such a design helps to reconstruct the original data more comprehensively and improve the prediction accuracy. Through a carefully designed decoder structure and training strategy, the accuracy of the total carbon emissions prediction can be significantly improved. Especially when faced with non-stationary time series, the decoder can better handle factors such as outliers, seasonal and cyclical changes, and provide more stable and reliable prediction results. In practical applications, the decoder can not only be used for static historical data analysis, but also support dynamic real-time prediction. When new carbon emission data continues to flow into the system, the decoder can instantly adjust the prediction model based on the latest information to maintain the timeliness and accuracy of the prediction results. In other words, the decoder can significantly improve the effect of total carbon emissions prediction through its powerful feature reconstruction capabilities, time-dependent recovery functions, and support for real-time data, thereby more accurately evaluating the carbon emissions of railway transportation engineering projects.

[0058] Among them, when each of the multiple carbon emission time series coding feature vectors respectively represents the carbon emission time series periodic coding characteristics of different time series scales, when performing feature aggregation, the inconsistent time series periodicity scales will make the carbon emission multi-time domain scale significantly aggregated coding vectors also have significant multi-scale time series distribution spatial structure differences due to the difference in time series periodicity scales, affecting the convergence consistency of the decoder, thereby affecting the accuracy of the total carbon emissions estimation value of the railway transportation project obtained by the total carbon emissions prediction module based on the decoder.

[0059] In a preferred example of the present application, the multi-temporal scale significant aggregation coding vector of carbon emissions is optimized, including: First, the absolute value sum and the square root of the sum of squares of all eigenvalues ​​of the multi-temporal scale significant aggregation coding vector of carbon emissions are calculated to obtain the first carbon emissions multi-temporal scale significant aggregation coding spatial structure value and the second carbon emissions multi-temporal scale significant aggregation coding spatial structure value, which can be expressed as follows: ; ; in, The first of all eigenvalue sets representing the multi-temporal scale significant aggregation coding vector of carbon emissions eigenvalues, Indicates the The corresponding first carbon emissions multi-temporal scale significant aggregation encoding spatial structure value, Indicates the The corresponding second carbon emission multi-temporal scale significant aggregation encoding spatial structure value; Secondly, for each eigenvalue of the multi-temporal scale significant aggregation coding vector of carbon emissions, the product of the eigenvalue and the number of eigenvalues ​​is calculated by subtracting the spatial structure value of the first multi-temporal scale significant aggregation coding of carbon emissions from the eigenvalue to obtain the long-range dependency value of the first multi-temporal scale significant aggregation coding of carbon emissions, which is expressed as follows: ; in, Indicates the The corresponding first carbon emissions are significantly aggregated and encoded with long-range dependency values ​​at multiple time scales. The number of eigenvalues ​​representing the significant aggregation coding vector of carbon emissions at multiple temporal scales; Then, the second carbon emission multi-time domain scale significant aggregation coding long-range dependency value is obtained by calculating the product of the square root of the number of eigenvalues ​​multiplied by the eigenvalue minus the second carbon emission multi-time domain scale significant aggregation coding spatial structure value, which is expressed as follows: ; in, Indicates the The corresponding second carbon emissions are significantly aggregated at multiple time scales to encode long-range dependency values; Next, the index value calculated by taking the first carbon emission multi-time domain scale significant aggregation coding long-range dependency value as the exponent of the natural constant and the inverse of the second carbon emission multi-time domain scale significant aggregation coding long-range dependency value are weighted summed to obtain the optimized eigenvalue corresponding to each eigenvalue, which is expressed as follows: ; in, Indicates the The corresponding optimized eigenvalue is , Represent different weight parameters respectively. Indicates the calculation of the inverse. Indicates the calculation of the exponential value with the natural constant as the base; Finally, the optimized eigenvalues ​​are combined into an optimized carbon emissions multi-temporal scale significant aggregation coding vector.

[0060] In view of the possible spatial structure loss in the high-dimensional space of the feature set of the carbon emission multi-time domain scale significant aggregation coding vector, which causes the decoder weight to implicitly infer spatial structure information based on the features, resulting in inconsistent convergence. The present application establishes a long-distance feature dependency relationship based on the spatial structure representation of the carbon emission multi-time domain scale significant aggregation coding vector relative to the overall feature scale of the carbon emission multi-time domain scale significant aggregation coding vector, so as to establish the feature local connectivity of the carbon emission multi-time domain scale significant aggregation coding vector, and capture the spatial ambiguous information of the object feature value through the unstructured feature value point prediction of the carbon emission multi-time domain scale significant aggregation coding vector, thereby improving the spatial inductive bias perception ability of the feature set of the carbon emission multi-time domain scale significant aggregation coding vector, improving the convergence consistency of the decoder, and improving the accuracy of the total carbon emissions estimation value of the railway transportation project obtained by the carbon emission multi-time domain scale significant aggregation coding vector through the total carbon emissions prediction module based on the decoder.

[0061] Specifically, the warning generation unit 152 is used to determine whether to generate the carbon emissions exceeding the standard warning based on the comparison between the estimated total carbon emissions of the railway transportation project and the expected total carbon emissions. That is, by comparing the estimated total carbon emissions of the railway transportation project with the expected total carbon emissions, the carbon emission management effect of the railway transportation project is evaluated, and when the actual carbon emissions exceed expectations, the carbon emissions exceeding the standard warning is automatically generated to prompt the relevant departments to take corresponding emission reduction measures and strategy adjustments in time to achieve long-term carbon emission control goals. In this way, strong technical support can be provided for the sustainable development of railway transportation projects, and contributions can be made to the realization of low-carbon transportation and environmental protection goals.

[0062] Specifically, after confirming that the total carbon emissions of the railway transportation project are expected to exceed the standard, the system will create a detailed warning message, including but not limited to the degree of excess, possible reasons, and recommended initial measures. The warning information is formatted in an easy-to-understand form to ensure that the recipient can quickly obtain key information.

[0063] Next, the early warning information is sent to the relevant parties responsible for emission reduction measures and strategy adjustments through pre-configured notification channels (such as email, SMS or dedicated platforms). The selection of these channels is based on the need for response speed and the customary usage of various departments to ensure that all necessary decision makers can obtain information and take action in a timely manner. Along with the early warning, the system provides a series of support tools and specific emission reduction suggestions, covering specific measures such as optimizing construction processes, improving material selection, and strengthening energy management, aiming to help relevant parties quickly develop and implement effective emission reduction plans. For example, the system can recommend alternative low-carbon materials, or propose solutions to optimize the use of mechanical equipment to reduce energy consumption, while providing historical data comparative analysis to assist decision makers in understanding the particularity of the current situation.

[0064] To ensure transparency and accountability, the system automatically generates detailed report documents to record the time, process and final results of each warning event. These documents not only help internal audits, but also provide compliance evidence for external regulators. All relevant communication records, decision documents and execution logs will be properly stored for future reference. In addition, the system continuously monitors carbon emissions and records the effects of measures taken. Based on the feedback results, the system evaluates the effectiveness of emission reduction measures and provides more accurate data support for future forecasts and warnings.

[0065] In summary, a railway transportation project carbon emission evaluation system based on the entire life cycle based on the embodiment of the present application is explained, which uses a sensor group to collect on-site construction data of railway transportation projects, and uses artificial intelligence technology based on deep learning to calculate the carbon emissions of on-site construction data on a daily basis. Then, by performing a time series analysis based on multiple time domain scales on the carbon emission data generated by the construction of the project, the regularity and trend characteristics of the carbon emission changes are excavated, and on this basis, the total carbon emissions of the railway transportation project over the entire life cycle are intelligently estimated, and then combined with the expected total carbon emissions, it is determined whether to generate a warning prompt for carbon emissions exceeding the standard. In this way, real-time monitoring and intelligent early warning of carbon emissions of railway transportation projects can be achieved, which helps to take measures in advance, optimize engineering design, reduce carbon emissions, and realize green and low-carbon railway transportation projects.

[0066] Furthermore, a carbon emission evaluation method for railway transportation projects based on the entire life cycle is also provided.

[0067] Figure 7 Flow chart of the carbon emission evaluation method of railway transportation engineering based on the whole life cycle according to the embodiment of the present application. Figure 7As shown, the carbon emission evaluation method for railway transportation projects based on the whole life cycle includes the following steps: S1, using a sensor group to collect on-site construction data of railway transportation projects to obtain a set of on-site construction data; S2, performing daily carbon emission accounting based on the set of on-site construction data to obtain a daily time queue of carbon emissions; S3, performing time series encoding based on singular spectrum decomposition on the daily time queue of carbon emissions to obtain multiple carbon emission time series encoding feature vectors; S4, performing feature dynamic optimization aggregation on the multiple carbon emission time series encoding feature vectors to obtain a carbon emission multi-time domain scale significant aggregation encoding vector; S5, based on the carbon emission multi-time domain scale significant aggregation encoding vector, determining whether to generate a carbon emission excess warning prompt.

[0068] The specific operations of each step in the above-mentioned railway transportation project carbon emission evaluation method based on the whole life cycle have been referred to above. Figures 1 to 6 It has been introduced in detail in the description of the carbon emission evaluation system for railway transportation projects based on the whole life cycle, and therefore, its repeated description will be omitted.

[0069] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0070] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0071] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0072] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0073] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A railway transportation project carbon emission evaluation system based on the entire life cycle, characterized by: include: A construction data collection module, used to collect on-site construction data of the railway transportation project using a sensor group to obtain a collection of on-site construction data; A carbon emission accounting module, used for performing daily carbon emission accounting based on the set of on-site construction data to obtain a daily time queue of carbon emissions; A time series coding module, used for performing time series coding on the day-level time queue of the carbon emissions based on singular spectrum decomposition to obtain a plurality of carbon emissions time series coding feature vectors; A feature dynamic optimization aggregation module is used to perform feature dynamic optimization aggregation on the multiple carbon emission time series coding feature vectors to obtain a carbon emission multi-time domain scale significant aggregation coding vector; The early warning prompt generation module is used to determine whether to generate an early warning prompt of carbon emissions exceeding the standard based on the multi-temporal scale significant aggregation coding vector of carbon emissions.

2. The railway transportation engineering carbon emission evaluation system based on the whole life cycle according to claim 1 is characterized in that: The carbon emission accounting module includes: A data segmentation unit, used for segmenting the set of on-site construction data by day to obtain a set of on-site construction data at the day level; The construction data carbon accounting unit is used to input each daily on-site construction data in the set of daily on-site construction data into the carbon emission accounting model to obtain the daily time queue of the carbon emission.

3. The railway transportation engineering carbon emission evaluation system based on the whole life cycle according to claim 2 is characterized in that: The timing coding module comprises: A sequence decoding unit, used for inputting the day-level time queue of carbon emissions into a sequence decoder based on singular spectrum decomposition to obtain a plurality of carbon emissions time series subsequences; The sequence encoding unit is used to input the multiple carbon emission time series subsequences into the sequence encoder based on the LSTM model respectively to obtain the multiple carbon emission time series encoding feature vectors.

4. The railway transportation engineering carbon emission evaluation system based on the whole life cycle according to claim 3 is characterized in that: The feature dynamic optimization aggregation module includes: A pseudo-anchor aggregation center calculation unit, used to calculate a pseudo-anchor aggregation center representation vector of multiple time-domain features of carbon emissions based on the characteristic static potential energy distribution of the multiple carbon emissions time-series encoding feature vectors; A dynamic aggregation unit is used to dynamically aggregate the multiple carbon emission time series coding feature vectors based on the aggregation movement direction of each carbon emission time series coding feature vector in the multiple carbon emission time series coding feature vectors relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain the carbon emission multi-time domain scale significant aggregation coding vector.

5. The railway transportation engineering carbon emission evaluation system based on the whole life cycle according to claim 4 is characterized in that: The pseudo anchor aggregation center calculation unit is used to: Inputting each of the plurality of carbon emission time series encoding feature vectors into a characteristic static potential energy measurement network to obtain a plurality of carbon emission time series characteristic static potential energy measurement coefficients; Inputting the plurality of carbon emission time series characteristic static potential energy measurement coefficients into a characteristic energy level screening gating unit to obtain a plurality of carbon emission time series characteristic static potential energy weight factors; Based on the static potential weight factors of the multiple carbon emission time series features, a weighted sum of the multiple carbon emission time series encoding feature vectors is calculated to obtain the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector.

6. The railway transportation engineering carbon emission evaluation system based on the whole life cycle according to claim 5 is characterized in that: The dynamic polymerization unit is used for: Calculating the aggregation movement direction of each carbon emission time series encoding feature vector in the multiple carbon emission time series encoding feature vectors relative to the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector to obtain multiple carbon emission time series feature aggregation movement directions; Based on the aggregation movement directions of the multiple carbon emission time series features, the multiple carbon emission time series coding feature vectors are dynamically aggregated toward the carbon emission multi-temporal feature pseudo-anchor aggregation center representation vector to obtain the carbon emission multi-temporal scale significant aggregation coding vector.

7. The railway transportation engineering carbon emission evaluation system based on the whole life cycle according to claim 6 is characterized in that: The carbon emission time series feature aggregation movement direction is the arccosine function value between the carbon emission time series encoding feature vector and the carbon emission multi-time domain feature pseudo-anchor aggregation center representation vector.

8. The railway transportation engineering carbon emission evaluation system based on the whole life cycle according to claim 7 is characterized in that: The early warning prompt generation module includes: A total carbon emission estimation unit, used for inputting the carbon emission multi-time domain scale significant aggregation coding vector into a decoder-based total carbon emission prediction module to obtain an estimated value of total carbon emission of railway traffic engineering; The warning generation unit is used to determine whether to generate a warning prompt of the carbon emissions exceeding the standard based on the comparison between the estimated value of the total carbon emissions of the railway transportation project and the expected total carbon emissions.

9. The carbon emission evaluation method for railway transportation projects based on the whole life cycle is characterized by: include: Using the sensor group to collect on-site construction data of the railway transportation project to obtain a collection of on-site construction data; Performing daily carbon emission accounting based on the set of on-site construction data to obtain a daily time queue of carbon emissions; Performing time series coding based on singular spectrum decomposition on the day-level time queue of the carbon emissions to obtain a plurality of carbon emissions time series coding feature vectors; Performing dynamic optimization aggregation on the multiple carbon emission time series coding feature vectors to obtain a carbon emission multi-time domain scale significant aggregation coding vector; Based on the multi-temporal scale significant aggregation coding vector of carbon emissions, it is determined whether to generate an early warning prompt of carbon emissions exceeding the standard.

Images