Carbon emission monitoring system and method for railway engineering green traffic

Abstract

The invention relates to the technical field of carbon emission monitoring, and particularly discloses a carbon emission monitoring system and method for railway engineering green traffic, and the method comprises the steps: firstly obtaining the actual power consumption in the train operation process from a train traction power supply system based on a preset time period; the method comprises the following steps: acquiring a train running area, synchronously acquiring a power grid carbon emission factor corresponding to the train running area, calculating the carbon emission of a train in each time period based on the power grid carbon emission factor, then further screening out high-carbon emission data items, calling train running state information in each high-carbon emission time period, and further calculating the train running state information based on a deep learning technology. According to the method, deep feature extraction and clustering analysis are carried out on train operation state information in each high-carbon emission time period, so that main influence factors causing high-carbon emission of a train are identified. According to the invention, refined attribution analysis of train carbon emission can be realized, and potential high-carbon emission events can be found and early warned in time, so that a scientific basis is provided for formulating a targeted energy-saving and emission-reducing strategy.

Description

Technical Field

[0001] This application relates to the technical field of carbon emission monitoring, and more specifically, to a carbon emission monitoring system and method for green transportation in railway engineering. Background Art

[0002] As a relatively environmentally friendly mode of transportation, railway transportation has significant advantages in energy conservation and emission reduction. Currently, with the expansion of the railway network and the increase in train operation frequencies, it has become particularly crucial to understand and optimize carbon emissions during train operation.

[0003] At the present stage, carbon emission monitoring in the railway system mainly relies on static models based on energy consumption estimation, and mostly uses fixed carbon emission coefficients (such as the average emission factor of the national power grid) to estimate carbon emissions, while ignoring the spatio-temporal differences in the energy structure of different regional power grids, and being unable to trace the coupling mechanism of multi-dimensional factors behind high carbon emission events, lacking the ability to dynamically attribute high carbon emission scenarios. For example, information such as train driving behavior (such as sudden acceleration operations), line conditions (such as sections with sudden slope changes), and power grid power supply characteristics (such as the energy structure of the power grid) has a synergistic impact on carbon emissions. Traditional carbon emission monitoring methods often have difficulty in dynamically monitoring and attributing the carbon emissions of train operation, resulting in a lack of clear direction when formulating energy conservation and emission reduction measures.

[0004] Therefore, there is a need to provide an optimized carbon emission monitoring system and method for green transportation in railway engineering to solve the above technical problems. Summary of the Invention

[0005] To solve the above technical problems, this application is proposed.

[0006] According to one aspect of this application, a carbon emission monitoring method for green transportation in railway engineering is provided, which includes: Obtaining the actual power consumption during train operation from the train traction power supply system based on a predetermined time period to obtain a time series of the actual power consumption, and at the same time obtaining the grid carbon emission factor corresponding to the train operation area from the grid energy management system based on the predetermined time period to obtain a time series of the grid carbon emission factor; Calculating a time series of train carbon emissions based on the time series of the actual power consumption and the time series of the grid carbon emission factor; Marking the data items in the time series of train carbon emissions that are greater than a preset carbon emission threshold as high emission time intervals, and obtaining the train operation data in the high emission time intervals to obtain a set of train operation state information; Performing cluster analysis on the set of train operation state information to determine the main influencing factors leading to high train carbon emissions.

[0007] According to another aspect of the present application, there is provided a carbon emission monitoring system for green transportation in railway engineering, which includes: A time-series data acquisition module, configured to obtain the actual power consumption during the train operation from the train traction power supply system based on a predetermined time period to obtain a time series of the actual power consumption, and at the same time obtain the grid carbon emission factor corresponding to the train operation area from the grid energy management system based on the predetermined time period to obtain a time series of the grid carbon emission factor; A carbon emission calculation module, configured to calculate a time series of the train carbon emissions based on the time series of the actual power consumption and the time series of the grid carbon emission factor; A high-emission identification module, configured to mark the data items in the time series of the train carbon emissions that are greater than a preset carbon emission threshold as high-emission time intervals, and obtain the train operation data in the high-emission time intervals to obtain a set of train operation state information; A clustering analysis module, configured to perform clustering analysis on the set of the train operation state information to determine the main influencing factors causing high train carbon emissions.

[0008] The present application has at least the following technical effects: Compared with the prior art, the carbon emission monitoring system and method for green transportation in railway engineering provided by the present application first obtain the actual power consumption during the train operation from the train traction power supply system based on a predetermined time period, and synchronously obtain the grid carbon emission factor corresponding to the train operation area. Based on this, the carbon emissions of the train in each time period are calculated. Then, the high-carbon emission data items are further screened out, and the train operation state information in each high-carbon emission time period is retrieved. Furthermore, based on deep learning technology, through deep feature extraction and clustering analysis of the train operation state information in each high-carbon emission time period, the main influencing factors causing high train carbon emissions are identified. The present application can achieve refined attribution analysis of train carbon emissions, timely discover and warn potential high-carbon emission events, thereby providing a scientific basis for formulating targeted energy-saving and emission-reduction strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] By describing the embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features, and advantages of the present application will become more obvious. The 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 to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0010] Figure 1 It is a flowchart of a carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application.

[0011] Figure 2 It is a flowchart of sub-step S4 of the carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application.

[0012] Figure 3 It is a schematic diagram of data flow of sub-step S4 of the carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application.

[0013] Figure 4 It is a flowchart of sub-step S42 of the carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application.

[0014] Figure 5 It is a flowchart of sub-step S422 of the carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application.

[0015] Figure 6 It is a block diagram of the carbon emission monitoring system for green transportation in railway engineering according to an embodiment of the present application. Detailed Description of the Invention

[0016] As shown in the present application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" 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.

[0017] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0018] 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 operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, as needed, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0019] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0020] It should be noted in advance that all information or data acquisition and processing in this application are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining the authorization from the authority manager.

[0021] Figure 1 FIG. is a flowchart of a carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application. As Figure 1 shown, the carbon emission monitoring method for green transportation in railway engineering includes the steps of: S1, obtaining the actual power consumption during the train operation from the train traction power supply system based on a predetermined time period to obtain a time series of the actual power consumption, and at the same time obtaining the grid carbon emission factor corresponding to the train operation area from the grid energy management system based on the predetermined time period to obtain a time series of the grid carbon emission factor; S2, calculating a time series of the train carbon emissions based on the time series of the actual power consumption and the time series of the grid carbon emission factor; S3, marking the data items in the time series of the train carbon emissions that are greater than a preset carbon emission threshold as high emission time intervals, and obtaining the train operation data in the high emission time intervals to obtain a set of train operation state information; S4, performing a clustering analysis on the set of train operation state information to determine the main influencing factors causing high carbon emissions of the train.

[0022] In the above carbon emission monitoring method for green transportation in railway engineering, in step S1, the actual power consumption during the train operation is obtained from the train traction power supply system based on a predetermined time period to obtain a time series of the actual power consumption, and at the same time the grid carbon emission factor corresponding to the train operation area is obtained from the grid energy management system based on the predetermined time period to obtain a time series of the grid carbon emission factor. It should be understood that the dynamic monitoring of railway carbon emissions needs to capture the spatio-temporal variation characteristics of both train energy consumption and grid carbon emission intensity simultaneously. Traditional methods using fixed carbon emission factors (such as the national annual average value) and monthly energy consumption statistics result in the calculation results being unable to reflect the true impact of the real-time energy structure of the grid (such as the intra-day fluctuations of wind power and photovoltaic power generation) on carbon emissions. Therefore, for trains operating across regions (such as passing through areas dominated by thermal power and areas rich in hydropower), by synchronously obtaining the power consumption of the traction power supply system and the regional grid carbon emission factor in this application, the carbon emission intensity of the train in different operation sections can be accurately calculated, avoiding the overestimation or underestimation of carbon emissions caused by fixed factors, thereby realizing the dynamic monitoring of train carbon emissions.

[0023] Specifically, since a train may cross multiple different power grid coverage areas, and there may be significant differences in the power grid energy structure (such as the proportion of wind power and photovoltaic power generation) in each area, it is necessary to dynamically adjust the carbon emission factors used according to the actual position of the train. Considering that the power grid energy structure fluctuates with factors such as time and weather conditions, it is particularly important to select an appropriate predetermined time period. The daytime power generation of some renewable energy sources (such as solar energy and wind energy) fluctuates greatly due to weather conditions, which means that if the predetermined time period is set too long, it may mask the impact of these short-term fluctuations on carbon emissions. On the contrary, if the time period is too short, it may lead to an excessive amount of data processing and increase the computational burden. Reasonably selecting the predetermined time period is one of the keys to ensuring the accuracy of the calculation results. Usually, a more appropriate predetermined time period can be determined based on the average running speed of the train and the change frequency of the power grid energy structure to balance the calculation accuracy and efficiency. For example, 15 minutes as a time period can capture the short-term fluctuations of the power grid energy structure without causing overly heavy data processing.

[0024] In the process of specific implementation, it is also necessary to establish an effective data verification mechanism to ensure the accuracy of the data obtained from the train traction power supply system and the power grid energy management system. This mechanism should include, but is not limited to, links such as checking the consistency of data formats, verifying data integrity, and identifying and processing outliers. For example, when abnormal data is detected in a certain time period, the system should automatically trigger an alarm and attempt to re-acquire or repair the data in that time period to ensure the continuity and integrity of the data link. In addition, some special situations during the train operation need to be considered. For example, when the train passes through a section with a sudden change in slope or performs a rapid acceleration operation, the energy consumption mode will change significantly. The data generated under these special circumstances is also important for understanding the carbon emission characteristics of the train. Therefore, when designing the data acquisition scheme, special attention should be paid to the data collection methods under these special working conditions to ensure that the data at these critical moments is not missed.

[0025] In addition, the impact of different seasons and weather conditions on the power grid energy structure needs to be considered. For example, in the hot summer weather, the increase in air-conditioning load will lead to an increase in the power grid load, thereby affecting the carbon emission factors of the power grid; while in winter, the increase in heating demand will have a similar effect. Therefore, when setting the predetermined time period, the impact of seasonal factors on the carbon emission factors of the power grid also needs to be considered. By introducing a more refined time division and a more flexible data acquisition strategy, it is ensured that the final calculation results can truly reflect the carbon emissions during the train operation.

[0026] To better address potential data loss or corruption issues, it is also necessary to build a powerful data backup and recovery mechanism. This includes not only the redundant design of data storage at the physical level but also the application of data verification and error correction algorithms at the logical level. For example, by using advanced error correction coding techniques, damaged data can be repaired to a certain extent, reducing the analysis deviation caused by data loss. At the same time, regularly performing data maintenance and cleaning tasks to remove redundant and outdated data and keep the database clean and operating efficiently is also an essential part of ensuring data quality.

[0027] In the above carbon emission monitoring method for green transportation in railway engineering, in step S2, based on the time series of the actual power consumption and the time series of the power grid carbon emission factor, the time series of the train carbon emissions is calculated. It should be understood that the traditional carbon emission accounting adopts a static mode of "total power consumption × fixed factor". Due to the differences in energy structures in different regions, the carbon emission intensity of the train when passing through the hydropower-rich area at night may be only 30% of that when passing through the coal-fired power grid area during the day. In this application, by multiplying the time series of the actual power consumption and the time series of the power grid carbon emission factor point by point, the carbon emissions of the train in each time period can be obtained, and a dynamic change curve of the carbon emissions can be constructed, which helps to accurately locate high-emission time periods and sections.

[0028] Specifically, to calculate the time series of the train carbon emissions, the time series of the actual power consumption needs to be multiplied by the time series of the power grid carbon emission factor point by point. This process can not only reflect the carbon emissions of the train in different time periods but also reveal the laws of the carbon emission intensity changing with time and space, which helps to accurately locate high-emission time periods and sections. To achieve this, seamless docking between data interfaces must be ensured so that the actual power consumption data of the train traction power supply system and the carbon emission factor data of the power grid energy management system can be matched on the same time basis. This means that the problem of cross-system and cross-departmental data sharing needs to be solved, an efficient data transmission channel needs to be established, and real-time data update and synchronous processing need to be ensured. Considering that the train may pass through multiple different power grid coverage areas, and the power grid energy structure (such as the proportion of wind power and photovoltaic power generation) in each area may vary significantly, during the data matching process, the carbon emission factor used needs to be dynamically adjusted according to the actual position of the train. Only in this way can it be ensured that the calculation results can truly reflect the carbon emission impact of the electric energy consumed during the train operation.

[0029] In the above-mentioned carbon emission monitoring method for green transportation of railway engineering, the step S3 marks the data items in the time series of the train carbon emissions that are greater than the preset carbon emission threshold as high emission time intervals, and obtains the train operation data in the high emission time interval to obtain a collection of train operation status information. It should be understood that since the optimization of train carbon emissions needs to be carried out preferentially for high emission scenarios, the present application further sets a preset carbon emission threshold to screen out high carbon emission events during train operation, so as to quickly locate the train operation conditions that need to be analyzed in detail, and extracts multi-dimensional train operation status information in each high emission time interval for in-depth analysis, in order to find carbon emission optimization space, and provide strong data support for the formulation of energy-saving and emission reduction measures. In a specific example of the present application, the train operation status information includes ambient temperature, ambient wind speed, running mileage, average train speed, track segment slope, track segment curvature, actual power consumption, grid carbon emission factor and train carbon emissions. Among them, the ambient temperature will affect the heat dissipation efficiency and cooling / heat demand of the train equipment, thereby affecting energy consumption; the ambient wind speed may affect the train's running resistance and aerodynamic performance; the running mileage and the average speed of the train reflect the overall running efficiency and energy consumption level of the train; the slope and curvature of the track section reflect the terrain undulations and turning changes during the train's operation, which directly affect the traction consumption and energy efficiency during the train's operation; and the actual power consumption directly reflects the energy consumption of the train during operation; the grid carbon emission factor reflects the carbon emission intensity of the electricity used by the train, revealing the impact of the energy structure of the power supply grid on carbon emissions; the train carbon emissions are the result of the combined effect of all the above factors, which directly reflects the carbon emission level during the train's operation. Through the comprehensive analysis of the above multi-dimensional information, it is helpful to identify the contribution of different influencing factors to the train's carbon emissions, thereby providing more refined guidance for the subsequent formulation of energy-saving and emission reduction strategies.

[0030] In the above-mentioned carbon emission monitoring method for green transportation of railway engineering, the step S4 performs cluster analysis on the set of train operation status information to determine the main influencing factors that lead to high carbon emissions of trains. Specifically, since high carbon emissions are usually the result of the coupling of multiple factors, traditional methods (such as linear regression) are difficult to resolve nonlinear correlations. For example, at the same slope, an increase in ambient wind speed may lead to a nonlinear increase in traction energy consumption. Therefore, the present application further introduces a deep learning algorithm, which performs deep feature extraction and cluster analysis on the train operation status information in each high emission time interval, so as to mine potential correlation patterns from multi-source heterogeneous data and identify the dominant influencing factors. Among them, Figure 2 This is a flowchart of sub-step S4 of the carbon emission monitoring method for green transportation of railway engineering according to an embodiment of the present application. Figure 3It is a data flow diagram of sub-step S4 of the carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application. As Figure 2 and Figure 3 shown, the step S4 includes the steps: S41, performing structured embedding encoding on each train operation status information in the set of train operation status information to obtain a set of train operation status feature embedding encoding vectors; S42, performing train operation status feature gain aggregation based on self-learning reinforcement on the set of train operation status feature embedding encoding vectors to obtain a train operation status feature aggregation analysis modeling vector; S43, performing a carbon emission influencing factor identification module based on the train operation status feature aggregation analysis modeling vector to obtain an identification result.

[0031] Specifically, in a specific example of the present application, the step S41 includes: inputting each train operation status information in the set of train operation status information into an embedding encoding module based on a multi-layer perceptron to obtain a set of train operation status feature embedding encoding vectors. It should be understood that since the train operation status information includes multi-source heterogeneous data such as environment, track, train operation conditions, and grid energy structure, its dimension is high and there are complex non-linear coupling relationships between parameters (such as the non-linear correlation between the slope and curvature of the track section and the average speed of the train). Directly using the original data for clustering analysis will lead to the "curse of dimensionality" and it is difficult to capture the deep interaction features between multi-source parameters. Therefore, the present application further performs embedding encoding on each train operation status information through a multi-layer perceptron (MLP) model to map the high-dimensional and heterogeneous operation status information to a low-dimensional continuous vector space, eliminating redundant noise while retaining key features, and providing a unified representation for subsequent analysis. Specifically, first, the train operation status information (environmental temperature, wind speed, slope, speed, etc.) within each time window is normalized and then spliced into an input vector, which is input into the multi-layer perceptron model. The multi-layer perceptron maps the input vector into a low-dimensional and continuous feature embedding encoding vector through a combination of multi-layer non-linear transformations and activation functions, thereby obtaining a set of train operation status feature embedding encoding vectors.

[0032] Specifically, in step S42, a self-learning reinforcement-based aggregation of train operation state feature gain is performed on the set of train operation state feature embedded coding vectors to obtain a train operation state feature aggregation analysis and modeling vector. It should be understood that the set of train operation state feature embedded coding vectors reflects the multi-dimensional features of the train operation state within each time window. Due to the time-varying nature of train operation conditions and external influencing factors, there are certain differences in the feature distributions of each train operation state feature embedded coding vector. To further extract key features that have a significant impact on train high carbon emissions from the train operation state feature embedded coding vectors of each high carbon emission time window, this application proposes a self-learning reinforcement-based method for aggregating train operation state feature gain. By performing clustering analysis on the set of train operation state feature embedded coding vectors, the global dominant pattern of the train operation state is mined, and the preliminary clustering results are used as the initial clustering centers for self-supervised learning. By evaluating the feature gain of each train operation state feature embedded coding vector, its gain contribution to train carbon emissions is determined, and then the clustering centers are adaptively adjusted towards the high-gain feature direction, so as to accurately capture the key features of train high carbon emissions and obtain the train operation state feature aggregation analysis and modeling vector. Among them, Figure 4 is a flowchart of sub-step S42 of the carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application. As Figure 4 shown, step S42 includes the steps of: S421, performing linear clustering analysis on the set of train operation state feature embedded coding vectors to obtain an initial linear clustering center coding vector of train operation state features; S422, calculating the linear clustering compensation component between the set of train operation state feature embedded coding vectors and the initial linear clustering center coding vector of train operation state features to obtain a linear clustering compensation component coding vector of train operation state features; S423, fusing the linear clustering compensation component coding vector of train operation state features and the initial linear clustering center coding vector of train operation state features to obtain the train operation state feature aggregation analysis and modeling vector.

[0033] More specifically, step S421 is represented by the formula: ; ; where, represents the set of train operation state feature embedded coding vectors, , , and respectively represent the 1st, 2nd, th and a train operation state feature embedding and encoding vector denotes the number of train operation state feature embedding and encoding vectors in the set of train operation state feature embedding and encoding vectors denotes the initial linear clustering center encoding vector of the train operation state feature

[0034] That is, by utilizing the global feature skeleton effect of linear clustering, the high-dimensional train operation state information is projected onto the low-dimensional subspace defined by the clustering center. By extracting the main linear components, both the global distribution law of the main energy consumption patterns is retained, and the high-frequency noise interference is filtered through low-rank approximation, forming a benchmark feature framework with physical significance. Through this linear clustering method, a dual-separation feature expression mechanism is constructed. The initial linear clustering center encoding vector of the generated train operation state feature, as an explicit representation of the linear structure, not only frames the macroscopic trend boundary of carbon emission changes but also compresses the non-linear coupling factors into the residual space, enabling the subsequent deep network to focus on exploring the deep non-linear attribution path, thereby improving the tracing accuracy and regulation effectiveness of sudden high-emission events.

[0035] Figure 5 is a flowchart of sub-step S422 of the carbon emission monitoring method for green transportation in railway engineering according to an embodiment of the present application. As Figure 5 shown, the step S422 includes steps: S4221, constructing a deep collaborative implicit encoding vector between each train operation state feature embedding and encoding vector in the set of train operation state feature embedding and encoding vectors and the initial linear clustering center encoding vector of the train operation state feature to obtain a set of train operation state feature deep collaborative implicit encoding vectors; S4222, based on the set of train operation state feature deep collaborative implicit encoding vectors, calculating a clustering compensation gain factor of each train operation state feature embedding and encoding vector in the set of train operation state feature embedding and encoding vectors relative to the initial linear clustering center encoding vector of the train operation state feature to obtain a set of train operation state clustering compensation gain factors; S4223, based on the set of train operation state clustering compensation gain factors, calculating a linear clustering compensation component encoding vector of the set of train operation state feature embedding and encoding vectors to obtain a train operation state feature linear clustering compensation component encoding vector.

[0036] In a specific example of the present application, the step S4221 includes: First, performing activation processing on the initial linear clustering center encoding vector of the train operation state feature based on the Sigmoid function to obtain an initial linear clustering center activation encoding vector of the train operation state feature, which is represented by the formula: ; Among them, represents the Sigmoid function, represents the initial linear clustering center activation coding vector of the train operation state characteristics.

[0037] That is, through the Sigmoid activation function, the linear coding value is compressed into the interval (0, 1), which can not only suppress the interference of extreme values, but also convert the physical quantity into a probabilistic representation, so that the initial linear clustering center activation coding vector of the generated train operation state characteristics retains the global correlation characteristics of the key parameters and enhances the non-linear sensitivity to secondary factors, thus providing a more discriminative feature input for the subsequent network layer.

[0038] Then, the initial linear clustering center activation coding vector of the train operation state characteristics is respectively cascaded and fused with each train operation state feature embedding coding vector in the set of the train operation state feature embedding coding vectors, and then input into the deep collaborative feature extraction network to obtain the set of the train operation state feature deep collaborative implicit coding vectors, which is expressed by the formula: ; Among them, represents the bias term, represents the weight matrix, represents the cascade function, represents the th train operation state feature deep collaborative implicit coding vector in the set of the train operation state feature deep collaborative implicit coding vectors.

[0039] That is, through the cascade fusion operation, the initial linear clustering center activation coding vector of the train operation state characteristics and the train operation state feature embedding coding vector are spliced with cross-level features, which not only retains the framework constraint of the linear clustering on the benchmark emission mode, but also injects the original fine-grained dynamic details. Furthermore, through the deep learning ability of the neural network, the deep non-linear collaborative features of the original train operation state feature embedding coding vector relative to the initial linear clustering center are automatically mined, forming a train operation state feature deep collaborative implicit coding vector with both global framework constraint and local detail sensitivity, providing a refined feature base with both interpretability and discriminability for the subsequent feature compensation gain calculation.

[0040] In a specific example of the present application, the step S4222 is expressed by the formula: ; Among them, represents the logarithmic function with base 2, represents the feature value at the th position in represents The eigenvalue at the th position, represents the feature scale of the feature depth collaborative implicit coding vector of the train operation state, represents the corresponding clustering compensation gain factor of the train operation state, represents the exponential function with base e.

[0041] That is, by introducing the calculation of the clustering compensation gain factor, the high-order feature information in the feature depth collaborative implicit coding vector of the train operation state is utilized to dynamically identify the differential performance of the carbon emission characteristics relative to the linear clustering benchmark under different operation scenarios, so as to realize the refined adjustment of the initial linear clustering structure based on the obtained clustering compensation gain factor of the train operation state, form a global non-linear compensation strategy, and further make the final clustering result more conform to the actual data distribution, effectively distinguish the key driving factors of high carbon emissions, provide causal-related decision support for formulating targeted energy conservation and emission reduction measures, and at the same time enhance the generalization ability and robustness of the model to complex scenarios.

[0042] Specifically, in a preferred example of the present application, the step S4223 includes: first, based on the synergy strength between each corresponding train operation state feature depth collaborative implicit coding vector and train operation state feature embedded coding vector in the set of train operation state feature depth collaborative implicit coding vectors and the set of train operation state feature embedded coding vectors, perform clustering balance correction on each train operation state clustering compensation gain factor in the set of train operation state clustering compensation gain factors to obtain the set of corrected train operation state clustering compensation gain factors, which is expressed by the formula: ; ; ; Among them, represents the calculation of the inner product, represents and the clustering active term between represents the variance of the set composed of all eigenvalues in the vector, represents the divergence factor related to the clustering active term is the clustering delay degree of represents the scattering relaxation effect of represents the exponential function with the natural constant as the base, represents the corrected train operation state clustering compensation gain factor, is the absolute value function.

[0043] Among them, when calculating the clustering compensation gain factor of the train operation state, considering that in addition to the original train operation state feature embedding coding vector, an incremental non-linear information of the linear clustering result based on the train operation state feature depth collaborative implicit coding vector is added, which leads to the addition of clustering elements in the clustering space, thus causing a systematic non-equilibrium state of the clustering space distribution. In response to this, the present application constructs a clustering active term to quantify the collaborative strength between the train operation state feature depth collaborative implicit coding vector and the train operation state feature embedding coding vector, and through establishing constraint conditions under the fractal structure, balances and corrects the train operation state clustering compensation gain factor, so that the train operation state clustering compensation gain factor can adaptively adjust the resonance amplitude during the propagation process in the fractal space, thereby suppressing the interference of abnormal energy fluctuations on the clustering stability, ensuring that the corrected compensation operator not only retains the non-linear correction advantage but also maintains the global energy balance of the clustering system, and realizing the optimization of the clustering equilibrium state under the fractal structure. In this way, based on the corrected train operation state clustering compensation gain factor for clustering incremental compensation, the clustering result can have stronger anti-noise ability and working condition adaptability while maintaining non-linear accuracy.

[0044] Then, perform normalization processing on the set of the corrected train operation state clustering compensation gain factors based on the Softmax function to obtain a set of normalized train operation state clustering compensation gain factors, which is expressed by the formula: ; Wherein, represents the softmax function, represents the corresponding normalized train operation state clustering compensation gain factor.

[0045] That is to say, by using the Softmax function to transform the corrected train operation state clustering compensation gain factor into a standardized parameter within the probability value range, not only the dimension difference between different feature dimensions is eliminated, but also the leading role of key compensation factors can be strengthened through the exponential decay mechanism, while suppressing secondary noise interference. Thus, based on the generated normalized train operation state clustering compensation gain factor, dynamic balance adjustment of the compensation increment can be achieved through probability space mapping. It should be understood that the processing of the Softmax function makes the probability value of each corrected train operation state clustering compensation gain factor positively correlated with its actual influence intensity, so that under the premise of maintaining the non-linear correction advantage, a weight distribution result that conforms to the cognitive logic is formed, solving the numerical instability problem of the original operator set, and also enhancing the anti-interference ability of the model through the global normalization characteristic of the probability distribution.

[0046] Finally, based on the set of the normalized train operation state clustering compensation gain factors, perform weighted aggregation on the set of the train operation state feature embedding coding vectors to obtain the train operation state feature linear clustering compensation component coding vector, which is expressed by the formula: ; where represents the train operation state feature linear clustering compensation component coding vector.

[0047] That is, through weighted aggregation, the local optimization of the normalized train operation state feature clustering compensation increment is transformed into the systematic improvement of the overall clustering structure. Specifically, the weight allocation mechanism based on the normalized train operation state clustering compensation gain factors can quantify the contribution degree differences of different operation state features to the correction of the clustering center, so that the weighted train operation state feature embedding coding vector not only retains the key information of the original feature distribution but also integrates the global adjustment effect of the non-linear compensation. Through this dynamic weighting method, an accurate compensation mapping for the linear clustering deviation is formed, so that the generated train operation state feature linear clustering compensation component coding vector can effectively reconcile the energy distribution contradiction between the original feature space and the clustering compensation space, and improve the stability and accuracy of the train operation state feature clustering result.

[0048] More specifically, the step S423 is expressed by the formula: ; where and represent different weight parameters, represents the train operation state feature aggregation analysis modeling vector.

[0049] That is, by organically integrating the global structure benchmark provided by the train operation state feature initial linear clustering center coding vector and the non-linear detail correction carried by the train operation state feature linear clustering compensation component coding vector, a composite feature representation that takes into account both macroscopic laws and microscopic fluctuations is formed. Through this fusion method, the generated train operation state feature aggregation analysis modeling vector becomes a bridge connecting the global statistical characteristics and local anomaly detection, providing a core parameter carrier with both physical interpretability and mathematical rigor for the subsequent carbon emission attribution analysis.

[0050] Specifically, in a specific example of the present application, step S43 includes: inputting the train operation state feature aggregation analysis modeling vector into a carbon emission influencing factor identification module based on a classifier to obtain an identification result, where the identification result includes the main influencing factors leading to high train carbon emissions and their corresponding confidence levels. Among them, the main influencing factors include environmental condition influencing factors, track terrain influencing factors, train operation condition influencing factors, and power grid energy structure influencing factors. Specifically, during the training process, the carbon emission influencing factor identification module based on the classifier uses the feature data of historical high carbon emission events and their corresponding influencing factor labels for supervised learning, continuously optimizing the model parameters to improve the identification accuracy. During the identification process, the classifier receives the train operation state feature aggregation analysis modeling vector as input, performs layer-by-layer feature analysis based on the learned classification decision boundary, and finally calculates the probability distribution of each influencing factor through the Softmax function of the output layer, that is, the main influencing factors leading to high train carbon emissions and their corresponding confidence levels, so as to provide an intuitive basis for energy conservation and emission reduction for train operation management. For example, when the identification result shows that environmental condition influencing factors (such as environmental temperature, wind speed) are the main factors leading to high train carbon emissions, measures such as adjusting the train operation time, strengthening train insulation or ventilation can be considered to reduce energy consumption; when track terrain influencing factors (such as slope, curvature) are dominant, optimizing the line design or adopting more energy-efficient train traction technology can be considered; when train operation condition influencing factors (such as train speed, acceleration control) are key, reducing carbon emissions can be achieved by optimizing the train operation strategy and improving driving efficiency; and when power grid energy structure influencing factors (such as carbon emission factors) are significant, measures such as optimizing the train dispatching strategy or promoting the transformation of the power grid energy structure can be considered to reduce carbon emissions.

[0051] In summary, the carbon emission monitoring method for green transportation in railway engineering based on the embodiments of the present application is elucidated. First, it obtains the actual power consumption during the train operation process from the train traction power supply system based on a predetermined time period, and synchronously obtains the power grid carbon emission factor corresponding to the train operation area. Based on this, it calculates the carbon emissions of the train in each time period. Then, it further screens out high carbon emission data items, retrieves the train operation state information in each high carbon emission time period, and further, based on deep learning technology, through deep feature extraction and clustering analysis of the train operation state information in each high carbon emission time period, to identify the main influencing factors leading to high train carbon emissions. In this way, refined attribution analysis of train carbon emissions can be achieved, potential high carbon emission events can be discovered and warned in a timely manner, thereby providing a scientific basis for formulating targeted energy conservation and emission reduction strategies.

[0052] Furthermore, a carbon emission monitoring system for green transportation in railway engineering is also provided.

[0053] Figure 6 It is a block diagram of a carbon emission monitoring system for green transportation in railway engineering according to an embodiment of the present application. As Figure 6 shown, the carbon emission monitoring system 100 for green transportation in railway engineering according to an embodiment of the present application includes: a timing data acquisition module 110, configured to obtain the actual power consumption during the train operation from the train traction power supply system based on a predetermined time period to obtain a time series of the actual power consumption, and at the same time obtain the grid carbon emission factor corresponding to the train operation area from the grid energy management system based on the predetermined time period to obtain a time series of the grid carbon emission factor; a carbon emission calculation module 120, configured to calculate a time series of the train carbon emissions based on the time series of the actual power consumption and the time series of the grid carbon emission factor; a high emission identification module 130, configured to mark the data items in the time series of the train carbon emissions that are greater than a preset carbon emission threshold as high emission time intervals, and obtain the train operation data during the high emission time intervals to obtain a set of train operation status information; a clustering analysis module 140, configured to perform clustering analysis on the set of train operation status information to determine the main influencing factors leading to high carbon emissions of the train.

[0054] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and easy understanding, rather than limitations, and the above details do not limit the present invention to necessarily adopt the above specific details to implement.

[0055] In the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions 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 embodiments described above are only illustrative. 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 shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0056] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, in any respect, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims concerned.

[0057] In addition, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The multiple elements stated in the system claims can also be implemented by one element through software or hardware.

[0058] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A carbon emission monitoring method for green transportation in railway engineering, characterized in that, Including: Obtaining the actual power consumption during the train operation from the train traction power supply system based on a predetermined time period to obtain a time series of the actual power consumption, and simultaneously obtaining the grid carbon emission factor corresponding to the train operation area from the grid energy management system based on the predetermined time period to obtain a time series of the grid carbon emission factor; Calculating a time series of the train carbon emissions based on the time series of the actual power consumption and the time series of the grid carbon emission factor; Marking the data items in the time series of the train carbon emissions that are greater than a preset carbon emission threshold as high emission time intervals, and obtaining the train operation data in the high emission time intervals to obtain a set of train operation state information; Performing a clustering analysis on the set of train operation state information to determine the main influencing factors causing high carbon emissions of the train.

2. The carbon emission monitoring method for green transportation in railway engineering according to claim 1, wherein The train operation state information includes environmental temperature, environmental wind speed, operating mileage, average train speed, track section gradient, track section curvature, actual power consumption, grid carbon emission factor, and train carbon emissions.

3. The carbon emission monitoring method for green transportation in railway engineering according to claim 2, characterized in that, Performing a clustering analysis on the set of train operation state information to determine the main influencing factors causing high carbon emissions of the train, including: Performing a structured embedding encoding on each train operation state information in the set of train operation state information to obtain a set of train operation state feature embedding encoding vectors; Performing a self-learning reinforcement-based train operation state feature gain aggregation on the set of train operation state feature embedding encoding vectors to obtain a train operation state feature aggregation analysis modeling vector; Performing a carbon emission influencing factor identification module based on the train operation state feature aggregation analysis modeling vector to obtain an identification result.

4. The carbon emission monitoring method for green transportation in railway engineering according to claim 3, characterized in that, Performing a structured embedding encoding on each train operation state information in the set of train operation state information to obtain a set of train operation state feature embedding encoding vectors, including: Inputting each train operation state information in the set of train operation state information into an embedding encoding module based on a multi-layer perceptron to obtain a set of train operation state feature embedding encoding vectors.

5. The carbon emission monitoring method for green transportation in railway engineering according to claim 4, characterized in that, Performing a self-learning reinforcement-based train operation state feature gain aggregation on the set of train operation state feature embedding encoding vectors to obtain a train operation state feature aggregation analysis modeling vector, including: Performing a linear clustering analysis on the set of train operation state feature embedding encoding vectors to obtain an initial linear clustering center encoding vector of the train operation state features; Calculating a linear clustering compensation component between the set of train operation state feature embedding encoding vectors and the initial linear clustering center encoding vector of the train operation state features to obtain a linear clustering compensation component encoding vector of the train operation state features; Fusing the linear clustering compensation component encoding vector of the train operation state features and the initial linear clustering center encoding vector of the train operation state features to obtain a train operation state feature aggregation analysis modeling vector.

6. The carbon emission monitoring method for green transportation in railway engineering according to claim 5, characterized in that Calculating a linear clustering compensation component between the set of train operation state feature embedding encoding vectors and the initial linear clustering center encoding vector of the train operation state features to obtain a linear clustering compensation component encoding vector of the train operation state features, including: Construct the deep collaborative implicit coding vectors between each train operation state feature embedding coding vector in the set of train operation state feature embedding coding vectors and the train operation state feature initial linear clustering center coding vector, so as to obtain the set of train operation state feature deep collaborative implicit coding vectors; Based on the set of train operation state feature deep collaborative implicit coding vectors, calculate the clustering compensation gain factors of each train operation state feature embedding coding vector in the set of train operation state feature embedding coding vectors relative to the train operation state feature initial linear clustering center coding vector, so as to obtain the set of train operation state clustering compensation gain factors; Based on the set of train operation state clustering compensation gain factors, calculate the linear clustering compensation component coding vectors of the set of train operation state feature embedding coding vectors, so as to obtain the train operation state feature linear clustering compensation component coding vectors.

7. The carbon emission monitoring method for green transportation in railway engineering according to claim 6, characterized in that, Construct the deep collaborative implicit coding vectors between each train operation state feature embedding coding vector in the set of train operation state feature embedding coding vectors and the train operation state feature initial linear clustering center coding vector, so as to obtain the set of train operation state feature deep collaborative implicit coding vectors, including: Perform activation processing on the train operation state feature initial linear clustering center coding vector based on the Sigmoid function to obtain the train operation state feature initial linear clustering center activation coding vector; After cascading and fusing the train operation state feature initial linear clustering center activation coding vector with each train operation state feature embedding coding vector in the set of train operation state feature embedding coding vectors respectively, input them into the deep collaborative feature extraction network to obtain the set of train operation state feature deep collaborative implicit coding vectors.

8. The carbon emission monitoring method for green transportation in railway engineering according to claim 7, characterized in that, Based on the set of train operation state clustering compensation gain factors, calculate the linear clustering compensation component coding vectors of the set of train operation state feature embedding coding vectors, so as to obtain the train operation state feature linear clustering compensation component coding vectors, including: Based on the collaborative strength between each pair of corresponding train operation state feature deep collaborative implicit coding vectors and train operation state feature embedding coding vectors in the set of train operation state feature deep collaborative implicit coding vectors and the set of train operation state feature embedding coding vectors, perform clustering balance correction on each train operation state clustering compensation gain factor in the set of train operation state clustering compensation gain factors, so as to obtain the set of corrected train operation state clustering compensation gain factors; Perform normalization processing on the set of corrected train operation state clustering compensation gain factors based on the Softmax function to obtain the set of normalized train operation state clustering compensation gain factors; Based on the set of normalized train operation state clustering compensation gain factors, perform weighted aggregation on the set of train operation state feature embedding coding vectors to obtain the train operation state feature linear clustering compensation component coding vectors.

9. The carbon emission monitoring method for green transportation in railway engineering according to claim 8, characterized in that Based on the train operation state feature aggregation analysis modeling vector, perform a carbon emission influencing factor identification module to obtain the identification result, including: Input the aggregated analysis and modeling vector of train operation state characteristics into the carbon emission influencing factor identification module based on a classifier to obtain an identification result, where the identification result includes the main influencing factors causing high train carbon emissions and their corresponding confidence levels. The main influencing factors include environmental condition influencing factors, track terrain influencing factors, train operation condition influencing factors, and power grid energy structure influencing factors.

10. A carbon emission monitoring system for green transportation in railway engineering, characterized in that, It includes: A time series data acquisition module, configured to obtain the actual power consumption during train operation from the train traction power supply system based on a predetermined time period to obtain a time series of the actual power consumption, and at the same time obtain the power grid carbon emission factor corresponding to the train operation area from the power grid energy management system based on the predetermined time period to obtain a time series of the power grid carbon emission factor; A carbon emission calculation module, configured to calculate a time series of train carbon emissions based on the time series of the actual power consumption and the time series of the power grid carbon emission factor; A high emission identification module, configured to mark the data items in the time series of train carbon emissions that are greater than a preset carbon emission threshold as high emission time intervals, and obtain the train operation data in the high emission time intervals to obtain a set of train operation state information; A clustering analysis module, configured to perform clustering analysis on the set of train operation state information to determine the main influencing factors causing high train carbon emissions.

Images