Method, system, device and medium for calculating carbon emission in port and shipping container transportation process

Abstract

The application provides a port container transportation process carbon emission accounting method, system, equipment and medium, belonging to the cross technical field of logistics carbon management and intelligent algorithm. The method comprises the following steps: collecting transportation and energy consumption data of road, waterway, railway and logistics storage links by classification, forming a standardized data set after pretreatment. Combining with industry standards and different transportation modes and cargo types, a carbon emission factor parameter library is created and dynamically updated through machine learning algorithm. Special accounting sub-models are constructed for different transportation modes, and carbon emission accounting is performed using corresponding formulas and parameters. The standardized data is input into the accounting sub-model, the carbon emission is calculated, and the optimal path is selected. The model parameters are calibrated using historical data to ensure accuracy. Finally, real-time data is collected and input into the accounting sub-model to generate a decision support report containing implementation steps, resource requirements and expected effects, helping to achieve low carbon and efficient management of the transportation process.

Description

Technical Field

[0001] This invention belongs to the technical field of logistics carbon management and intelligent algorithms, and more specifically, it relates to a method, system, equipment and medium for carbon emission accounting in port and shipping container transportation. Background Technology

[0002] Driven by the global wave of low-carbon development and the national green energy and "dual-carbon" strategies, the port and shipping sector has an increasingly urgent need for carbon emission management. Energy regulatory agencies are continuously strengthening carbon emission control requirements, and port and shipping companies are actively exploring low-carbon and zero-carbon approaches. The demand for carbon reduction assessment services for green logistics and transportation is particularly prominent in the container logistics and transportation sector. Establishing a carbon reduction accounting system for green logistics and transportation modes such as sea-rail intermodal transport and water-to-water transshipment, and providing accurate multimodal transport carbon reduction accounting optimization and screening services, has become a key measure to improve logistics efficiency, reduce costs, decrease carbon emissions, and enhance the green competitiveness of enterprises.

[0003] However, current carbon emission accounting technologies in the port and shipping container transportation sector have significant limitations and have not yet formed a carbon management capability covering the entire process. The flow of container cargo involves complex scenarios such as diverse transport vehicles, complex transport types, and numerous transshipment points, making it difficult to track cargo carbon emissions and posing many challenges to carbon management, thus failing to meet the actual needs of refined management.

[0004] One of the core shortcomings of existing carbon emission accounting technologies lies in the reliance on a single data source. Current accounting methods largely depend on internal enterprise statistics, lacking effective support from collaborative data across the supply chain and third-party monitoring data. This results in a one-sided accounting perspective and low data accuracy. This data acquisition model cannot comprehensively reflect the true carbon emissions across the entire transportation chain, leading to discrepancies between the accounting results and actual emissions, making it difficult to serve as a reliable basis for carbon management decisions.

[0005] Another key issue lies in the limitations of the algorithmic models. Existing accounting models have fixed logic, making it impossible to dynamically adjust the calculation logic based on the production characteristics and transportation scenarios of different industries. This results in difficulties in effectively connecting carbon emission data across different stages, leading to poor model versatility. Furthermore, the lack of a unified standard for carbon emission factor values ​​and the absence of a regular update mechanism further reduce the scientific rigor and accuracy of the accounting results. Moreover, for multimodal transport, a mainstream transportation mode, existing technologies fail to comprehensively encompass and accurately calculate carbon emissions at each logistics node, easily leading to omissions of details. The accounting results are susceptible to interference from human factors or missing data, severely hindering the improvement of carbon management in port and shipping container transportation. Summary of the Invention

[0006] To address the above issues, the present invention aims to provide a method, system, equipment, and medium for carbon emission accounting in port and shipping container transportation. By integrating multi-source data from internal and external sources, constructing an industry-adaptive mechanism, and introducing an intelligent AI model, the invention enhances the comprehensiveness, universality, and anti-interference capabilities of carbon accounting, providing high-precision data support for carbon emission control in green container transportation.

[0007] To achieve the above objectives, the present invention employs the following technical solution:

[0008] In a first aspect, embodiments of this application provide a method for carbon emission accounting in port and shipping container transportation processes, including:

[0009] Transportation data and energy consumption data from road, waterway, and rail transportation and logistics storage are collected in categories, preprocessed, and then stored in categories to form a standardized dataset.

[0010] In accordance with industry standards, and taking into account different modes of transportation and types of goods, a parameter library containing various carbon emission factors was created, and a dynamic update mechanism was established. Historical data was analyzed through machine learning algorithms, and various carbon emission factors were updated regularly.

[0011] For each mode of transportation—road, waterway, and rail—a separate accounting sub-model is constructed. Each sub-model is used to calculate carbon emissions based on the characteristics and data of the specific mode of transportation, employing appropriate formulas and parameters.

[0012] The standardized dataset is input into the corresponding accounting sub-model to calculate carbon emissions and select the optimal carbon emission path.

[0013] The sub-model was calibrated using multiple sets of historical data, and the model parameters were adjusted.

[0014] Real-time data collection of transportation and energy consumption data from highway, waterway, and railway transportation and logistics storage is conducted. After preprocessing, the data is input into the corresponding accounting sub-model. The accounting sub-model is then run to obtain carbon emission results for each route, select the optimal carbon emission route, and generate a decision support report that includes implementation steps, resource requirements, and expected effects.

[0015] In an optional implementation, the classified collection of transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage links, after preprocessing, is classified and stored to form a standardized dataset, including:

[0016] Collect transportation data and energy consumption data in the road transportation process, including vehicle fuel supply type, refrigerant filling table for cold boxes, average vehicle fuel consumption, and route information;

[0017] Collect transportation data and energy consumption data in the waterway transportation process, including ship fuel supply type, refrigerant filling table for cold boxes, average ship fuel consumption, and route information;

[0018] Collect transportation data and energy consumption data in the railway transportation process, including train fuel supply type, refrigerant filling table for cold boxes, average train fuel consumption, and route information;

[0019] Collect transportation and energy consumption data in the logistics and storage process, including energy consumption of ships at port and shore power usage of ships at port;

[0020] Collect information on transportation methods, historical carbon emission data, and related environmental data;

[0021] The collected data undergoes a cleaning process to remove outliers and fill in missing values. Data units and formats are standardized, and the data is categorized and stored according to different stages and data types in the cargo transportation process to form a standardized dataset.

[0022] In an optional implementation, the calculation sub-models are constructed for each of the road, waterway, and rail transportation modes, including:

[0023] For road, waterway, and rail transportation modes, carbon accounting operator models are constructed for road transportation, logistics and storage, waterway transportation, and rail transportation, respectively.

[0024] The road transport carbon accounting sub-model uses the mileage method to calculate carbon dioxide emissions, including:

[0025]

[0026] In the formula, C 公路,i For the carbon dioxide emissions of vehicle type i, F 油耗,i Let E be the unit average fuel consumption of vehicle type i. 燃料,i The greenhouse gas emission factor of fuels used by vehicles, C 逸散,j T represents the direct greenhouse gas emissions from the j-th fugitive source. i The freight turnover of vehicle type i is calculated using the formula T. i =W i ×D i W i D represents the weight of the goods. i For transportation distance;

[0027] For refrigerated container transportation, the emissions from fugitive sources are calculated using the following formula:

[0028]

[0029] Among them, R j Let P be the charge amount of the j-th refrigerant. GWP,j Let K be the global warming potential of the j-th escape source. 逸散,j Let be the dissipation coefficient of the j-th dissipation source;

[0030] The logistics storage carbon accounting sub-model includes a loading and unloading operation carbon accounting model and a cold storage carbon accounting model;

[0031] The carbon accounting model for loading and unloading operations includes:

[0032]

[0033] Among them, C 装卸 For greenhouse gas emissions from loading and unloading operations, C 燃料,k Let F be the average fuel consumption of the k-th type of loading and unloading equipment. 油耗,k Let E be the unit fuel consumption of the k-th loading and unloading equipment. 燃料,k Greenhouse gas emission factors of fuel used for loading and unloading equipment;

[0034] The carbon accounting models for refrigerated storage include:

[0035]

[0036] Among them, C 冷藏 R represents the direct greenhouse gas emissions from the cold storage process. l P is the amount of refrigerant added to the refrigeration equipment. GWP,l K represents the global warming potential of the refrigerant. 逸散,l This is the refrigerant dispersion coefficient.

[0037] In an optional implementation, the waterway transport carbon accounting sub-model includes a navigation process carbon accounting model and a port berthing process carbon accounting model;

[0038] The carbon accounting model for navigation includes:

[0039]

[0040] Among them, C 水路,m T represents the carbon dioxide emissions of type m ships. m For the freight turnover of type m ships, F 油耗,m E represents the fuel consumption per ton-kilometer for type m ships. 燃料,m Greenhouse gas emission factor of fuel used in ships, C 逸散,n Let n be the direct greenhouse gas emissions from the nth fugitive source.

[0041] The carbon accounting model for the berthing process includes:

[0042] When ships use shore power When the ship is not using shore power, ;

[0043] Among them, C 靠港 E represents greenhouse gas emissions during the berthing process. 岸电 E represents shore power usage during ship berthing. 电力 For the greenhouse gas emission factor of electricity, t o For the duration of a ship's berthing, P o For the power of marine auxiliary machinery, E 燃油,o Greenhouse gas emission factors for marine fuel oil;

[0044] The emission reductions from replacing fuel oil with shore power can be calculated using the following formula:

[0045]

[0046] Among them, R 替代 To reduce carbon dioxide emissions by using shore power instead of fuel oil, B p E represents the unit fuel consumption rate for power generation of marine diesel generators. 燃油,p Greenhouse gas emission factors for ship fuel oil.

[0047] In one optional implementation, the railway transport carbon accounting sub-model includes a diesel locomotive carbon accounting model and an electrified railway carbon accounting model;

[0048] The carbon accounting model for internal combustion locomotives includes:

[0049]

[0050] Among them, C 铁路,q V represents the greenhouse gas emissions from internal combustion locomotives. q F represents the estimated consumption of the q-th type of fuel for the locomotive. 油耗,q E represents the fuel consumption rate of the locomotive. 燃料,q E is the greenhouse gas emission factor for fuels. 供应,q Greenhouse gas emission factors in the fuel supply process;

[0051] The carbon accounting model for electrified railways includes:

[0052]

[0053] Among them, C 电气,r V represents greenhouse gas emissions from electrified railway locomotives. r E represents the estimated power consumption of the r-th type of locomotive. 电力,r Greenhouse gas emission factors for purchased electricity.

[0054] In an optional implementation, the step of inputting the standardized dataset into the corresponding accounting sub-model, calculating carbon emissions, and selecting the optimal carbon emission pathway includes:

[0055] The standardized dataset is input into the corresponding sub-model. First, the objective function and constraints are determined using linear programming, nonlinear programming, or dynamic programming optimization methods. The preliminary optimal carbon emission path is obtained by solving for the optimal solution. Then, machine learning algorithms are used to train the model on historical data so that the model can predict the carbon emission results of different paths. The optimal carbon emission path is then selected from the preliminary optimal carbon emission path.

[0056] In an optional implementation, the calibration of the sub-model using multiple sets of historical data and the adjustment of model parameters include:

[0057] The accounting sub-model is calibrated using multiple sets of historical data. The carbon emissions simulated by the accounting sub-model for a certain period in the past are compared with the actual carbon emissions. If the difference in carbon emissions exceeds a preset threshold, the relevant parameters are adjusted.

[0058] The accuracy of the accounting sub-model's prediction of future carbon emissions is verified by using reserved historical data or cited research data. If the verification fails, the model parameters are adjusted.

[0059] Secondly, embodiments of this application also provide a carbon emission accounting system for port and shipping container transportation processes, including:

[0060] The multi-source data acquisition and preprocessing module is used to collect transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage in a classified manner. After preprocessing, the data is classified and stored to form a standardized dataset.

[0061] The carbon factor parameter library construction module is used to create a parameter library containing various carbon emission factors according to industry standards and in combination with different modes of transportation and cargo types, and to establish a dynamic update mechanism. It analyzes historical data through machine learning algorithms and updates various carbon emission factors regularly.

[0062] The intelligent accounting model construction module is used to build accounting sub-models for different modes of transportation such as road, waterway, and railway. Each accounting sub-model is used to calculate carbon emissions based on the characteristics and data of the specific mode of transportation, using corresponding formulas and parameters.

[0063] The model training and optimization module is used to input standardized datasets into the corresponding sub-models, calculate carbon emissions, and select the optimal carbon emission pathways.

[0064] The model calibration and validation module is used to calibrate the sub-model using multiple sets of historical data and adjust the model parameters.

[0065] The model execution module is used to collect real-time transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage. After preprocessing, the data is input into the corresponding accounting sub-model. The accounting sub-model is run to obtain carbon emission results for each path, select the optimal carbon emission path, and generate a decision support report that includes implementation steps, resource requirements, and expected effects.

[0066] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the carbon emission accounting method for port and shipping container transportation as described in any of the above.

[0067] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the carbon emission accounting method for port and shipping container transportation as described in any of the above claims.

[0068] As can be seen from the above technical solutions, the present invention has the following advantages:

[0069] The carbon emission accounting method for port and shipping container transportation provided in this application involves multi-source data collection and preprocessing, the construction of a dynamically updated carbon factor parameter library in conjunction with industry standards, the development of accounting sub-models for different modes of transportation, the application of optimization methods and machine learning algorithms to select the optimal carbon emission path, and the accuracy of the results through model calibration and verification. This method achieves accurate accounting and effective optimization of carbon emissions in port and shipping container transportation, provides a scientific basis for decision-making, helps reduce carbon emissions, improve transportation efficiency, and reduce environmental impact, and has significant environmental and economic benefits.

[0070] This application ensures high-quality input data through multi-source data acquisition and standardized preprocessing, providing a solid data foundation for subsequent carbon emission accounting, reducing accounting deviations caused by data quality issues, and improving the credibility of the entire accounting process.

[0071] This application constructs specialized accounting sub-models for different modes of transportation such as highways, waterways, and railways, and calculates carbon emissions by combining specific transportation characteristics and professional formulas. This enables accurate quantification of carbon emissions at each stage of the transportation process, which helps to identify key links and main sources of carbon emissions.

[0072] This application uses optimization algorithms and machine learning techniques to analyze the calculation results, which can screen out the optimal carbon emission path, provide a scientific basis for transportation decisions, and help enterprises reduce carbon emissions to the greatest extent while meeting transportation needs, thus achieving the goal of green transportation.

[0073] This application promotes the low-carbon development of port and shipping container transportation through precise accounting and route optimization, effectively reducing greenhouse gas emissions. It is of great significance for mitigating climate change and improving environmental quality, and is in line with the trend and requirements of sustainable development.

[0074] The optimized transportation routes proposed in this application not only reduce carbon emission costs but may also bring direct economic benefits such as reduced fuel consumption. At the same time, companies actively practicing low-carbon transportation can enhance their social image and market competitiveness, better adapting to increasingly stringent environmental policies and market demands for green logistics. Attached Figure Description

[0075] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0076] Figure 1 A flowchart illustrating the carbon emission accounting method for port and shipping container transportation provided in this application.

[0077] Figure 2 This is a schematic diagram of the carbon emission accounting system for port and shipping container transportation provided in this application.

[0078] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0079] The various embodiments of this disclosure will be described more fully in the following detailed description of the specific steps of the carbon emission accounting method for port and shipping container transportation. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0080] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0081] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0082] Please see Figure 1 The diagram shows a flowchart of a method for carbon emission accounting in port and shipping container transportation, as described in a specific embodiment. The method includes:

[0083] S1: Collect transportation data and energy consumption data from road, waterway, and rail transportation and logistics storage, classify and store them after preprocessing, and form a standardized dataset.

[0084] In specific implementations, data collection is fundamental to carbon emission accounting during port and shipping container transportation. Firstly, for road transport, we need to collect data on vehicle fuel supply types, refrigerant refill schedules for refrigerated containers, average vehicle fuel consumption, and route information. This information helps us understand the energy consumption of road transport. For example, the vehicle fuel supply type determines its carbon emission potential, while average vehicle fuel consumption directly reflects the energy efficiency during transportation. Simultaneously, route information such as origin, destination, waypoints, distance traveled, road type, and traffic restrictions are crucial for assessing the carbon emissions of road transport.

[0085] For waterway transportation, key data points include ship fuel supply type, refrigerant charge levels in refrigerated containers, average fuel consumption, and route information. Fuel supply type and average fuel consumption reflect a ship's energy utilization, while route information helps assess carbon emissions on different routes. Data collection for rail transportation is similar to that for road and waterway transportation, including train fuel supply type, refrigerant charge levels in refrigerated containers, average fuel consumption, and route information. This data helps us understand the energy consumption and carbon emission characteristics of rail transportation.

[0086] Data collection in the logistics and storage phase focuses on the energy consumption of ships at port, including energy used for loading and unloading (such as loading and unloading ships, horizontal transportation, and terminal storage), shore power consumption (if used), and port berthing duration. This data reflects energy consumption during the logistics and storage process and is crucial for accurately calculating carbon emissions.

[0087] In addition to the data from the transportation process mentioned above, we also need to collect information on transportation modes (such as single modes or multimodal transport combinations like road, rail, and waterway), historical carbon emission data, and relevant environmental data (such as temperature and wind speed). This data helps us to have a more comprehensive understanding of carbon emissions during transportation and provides support for subsequent model training and optimization.

[0088] After collecting this data, preprocessing is required. Preprocessing includes removing outliers, imputing missing values, standardizing data units and formats, and classifying and storing the data according to different stages and data types in the cargo transportation process, ultimately forming a standardized dataset. For example, when removing outliers, statistical methods can be used to identify and remove data points that significantly deviate from the normal range; when imputing missing values, interpolation methods or estimation methods based on historical data can be used to supplement the missing data. Standardizing data units and formats ensures that data from different sources can be integrated and analyzed within the same accounting framework. Categorized storage involves organizing the data according to dimensions such as transportation mode and cargo type, so that subsequent accounting sub-models can quickly and accurately obtain the required data.

[0089] This step enables the acquisition of high-quality, standardized datasets, providing a solid data foundation for subsequent carbon emission accounting.

[0090] S2: In accordance with industry standards, and in combination with different modes of transportation and types of goods, create a parameter library containing various carbon emission factors, and establish a dynamic update mechanism. Analyze historical data through machine learning algorithms and update various carbon emission factors regularly.

[0091] In specific implementations, constructing a carbon factor parameter database is a crucial step in carbon emission accounting. Specifically, this step, based on national, industry, and international standards and considering different modes of transportation and cargo types, creates a comprehensive parameter database that includes tables of carbon emission factor numbers, carbon intensity tables, global warming potential values ​​for fugitive sources, greenhouse gas emission factors for fuels, greenhouse gas emission factors for fuel supply, refrigeration fugitives, greenhouse gas emission factors for electricity, and greenhouse gas emission factors for alternative fuels.

[0092] The construction of this parameter database requires full consideration of the impact of various factors on carbon emissions. For example, the greenhouse gas emission coefficient for fuels needs to be accurately measured and recorded based on the carbon dioxide emissions produced during the combustion of different types of fuels (such as gasoline, diesel, and natural gas). Meanwhile, the global warming potential table for fugitive sources needs to consider the impact of substances such as refrigerants on the climate after they are released, and its global warming potential value needs to be determined through scientific research and experimental data.

[0093] To ensure the accuracy and timeliness of the parameter database, this method establishes a dynamic update mechanism. By analyzing historical data using machine learning algorithms (such as time series analysis), the changing trends of carbon emission factors can be predicted, and the database can be updated regularly based on these predictions. For example, when new research results indicate changes in the greenhouse gas emission coefficient of a certain fuel, or when policies impose new requirements on carbon emission accounting methods, the corresponding data in the parameter database can be adjusted in a timely manner to reflect the latest situation.

[0094] This dynamic update mechanism enables the carbon factor parameter library to adapt to constantly changing realities, providing reliable parameter support for carbon emission accounting.

[0095] S3: For each mode of transportation, such as road, waterway, and rail, a separate accounting sub-model is constructed. The carbon emission is then calculated using the corresponding formulas and parameters based on the characteristics and data of the specific mode of transportation.

[0096] In a specific implementation, when constructing the intelligent accounting model, we build dedicated accounting sub-models for different modes of transportation, such as highways, waterways, and railways. Each sub-model calculates carbon emissions using corresponding formulas and parameters based on the characteristics and data of the specific transportation mode.

[0097] For the carbon accounting sub-model of road transport, we use the mileage method to calculate carbon dioxide emissions. The specific formula is:

[0098]

[0099] Among them, C 公路,i T represents the carbon dioxide emissions of vehicle type i. iIt is the freight turnover of vehicle type i (calculated by formula T). i =W i ×D i W i D represents the weight of the goods. i (for transport distance), F i Let E be the unit average fuel consumption of vehicle type i. i The greenhouse gas emission factor of fuels used by vehicles, C 逸散,j Let be the direct greenhouse gas emissions from the j-th fugitive source. For refrigerated container transport, we also need to use the formula... To calculate fugitive emissions, where R j Let P be the charge amount of the j-th refrigerant. GWP,j Let K be the global warming potential of the j-th escape source. 逸散,j Let be the emission coefficient of the j-th emission source.

[0100] In the carbon accounting sub-model for logistics storage, we include a carbon accounting model for loading and unloading operations and a carbon accounting model for refrigerated storage. The formula for the carbon accounting model for loading and unloading operations is:

[0101]

[0102] Here, C 装卸 For greenhouse gas emissions from loading and unloading operations, C 燃料,k Let F be the average fuel consumption of the k-th type of loading and unloading equipment. 油耗,k Let E be the unit fuel consumption of the k-th loading and unloading equipment. 燃料,k Greenhouse gas emission factors of fuel used for loading and unloading equipment.

[0103] For the carbon accounting model of refrigerated storage, we use the following formula:

[0104]

[0105] Among them, C 冷藏 R represents the direct greenhouse gas emissions from the cold storage process. l P is the amount of refrigerant added to the refrigeration equipment. GWP,l K represents the global warming potential of the refrigerant. 逸散,l This is the refrigerant dispersion coefficient.

[0106] The carbon accounting sub-model for waterway transportation includes a carbon accounting model for the navigation process and a carbon accounting model for the berthing process. The formula for the carbon accounting model for the navigation process is:

[0107]

[0108] Among them, C 水路,m T represents the carbon dioxide emissions of type m ships. mFor the freight turnover of type m ships, F 油耗,m E represents the fuel consumption per ton-kilometer for type m ships. 燃料,m Greenhouse gas emission factor of fuel used in ships, C 逸散,n Let be the direct greenhouse gas emissions from the nth fugitive source.

[0109] The carbon accounting model for the berthing process is divided into two scenarios based on whether the ship uses shore power. When the ship uses shore power... When the ship is not using shore power, Among them, C 靠港 E represents greenhouse gas emissions during the berthing process. 岸电 E represents shore power usage during ship berthing. 电力 For the greenhouse gas emission factor of electricity, t o For the duration of a ship's berthing, P o For the power of marine auxiliary machinery, E 燃油,o This is the greenhouse gas emission factor of marine fuel oil. Furthermore, we can also use the formula R... 替代 =E 岸电 ×B p ×E 燃油,p To calculate the emissions reduction from replacing fuel oil with shore power, where R 替代 To reduce carbon dioxide emissions by using shore power instead of fuel oil, B p E represents the unit fuel consumption rate for power generation of marine diesel generators. 燃油,p Greenhouse gas emission factors for ship fuel oil.

[0110] The carbon accounting sub-model for railway transportation encompasses carbon accounting models for diesel locomotives and electrified railways. The formula for the carbon accounting model for diesel locomotives is:

[0111]

[0112] Among them, C 铁路,q V represents the greenhouse gas emissions from internal combustion locomotives. q F represents the estimated consumption of the q-th type of fuel for the locomotive. 油耗,q E represents the fuel consumption rate of the locomotive. 燃料,q E is the greenhouse gas emission factor for fuels. 供应,q Greenhouse gas emission factors in the fuel supply process.

[0113] For the carbon accounting model of electrified railways, the formula used is:

[0114]

[0115] Here, C 电气,r V represents greenhouse gas emissions from electrified railway locomotives. rE represents the estimated power consumption of the r-th type of locomotive. 电力,r Greenhouse gas emission factors for purchased electricity.

[0116] By constructing these detailed accounting sub-models, this method can accurately calculate the carbon emission characteristics of different modes of transportation, providing a scientific basis for subsequent route optimization and decision support.

[0117] S4: Input the standardized dataset into the corresponding sub-model to calculate carbon emissions and select the optimal carbon emission path.

[0118] In a specific implementation, after data collection, preprocessing, and intelligent accounting model construction are completed, the standardized dataset is input into the corresponding accounting sub-model to start calculating carbon emissions and selecting the optimal carbon emission path.

[0119] First, optimization methods such as linear programming, nonlinear programming, or dynamic programming are used to determine the objective function and constraints. For example, in linear programming, total carbon emissions can be used as the objective function, aiming to minimize it; simultaneously, a series of constraints are set based on actual transportation needs and limitations (such as freight transportation time and transportation costs). By solving this optimization model, a preliminary optimal carbon emission path can be obtained.

[0120] However, to further improve the accuracy and adaptability of path optimization, machine learning algorithms are also used to train on historical data. Machine learning models (such as neural networks and decision trees) can learn patterns and trends in historical carbon emission data, thereby predicting the carbon emission outcomes of different paths. Based on these predictions, better paths can be selected from the initial optimal carbon emission paths, making them more consistent with reality and future trends.

[0121] This path optimization strategy, which combines optimization methods and machine learning techniques, can not only help us find the optimal carbon emission path under current conditions, but also continuously improve the optimization results as data accumulates and models are updated, providing strong support for carbon emission management in port and shipping container transportation.

[0122] S5: Use multiple sets of historical data to calibrate the sub-model and adjust the model parameters.

[0123] In specific implementations, to ensure the accuracy and reliability of the accounting sub-model, it is necessary to calibrate and validate it using multiple sets of historical data. During calibration, this step compares the carbon emissions simulated by the accounting sub-model for a past period with the actual carbon emissions. If the difference in carbon emissions exceeds a preset threshold, the relevant parameters need to be adjusted. For example, if the carbon emissions predicted by the model are significantly lower than the actual values, it may be necessary to re-examine the input carbon emission factors or transportation data, check for underestimation, and adjust the model parameters accordingly.

[0124] Simultaneously, the accuracy of the accounting sub-model's predictions of future carbon emissions is verified using reserved historical data or data from other authoritative studies. If the verification results show that the model's predictive performance is poor, it is necessary to return to the previous step and further adjust and optimize the model framework or parameters. This process may require multiple iterations until the model can stably output accurate prediction results.

[0125] This rigorous calibration and verification process ensures the accuracy and reliability of the accounting sub-model in practical applications, providing a solid guarantee for its decision support role in carbon emission management.

[0126] S6: Real-time collection of transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage links. After preprocessing, the data is input into the corresponding accounting sub-model. The accounting sub-model is run to obtain carbon emission results for each path, select the optimal carbon emission path, and generate a decision support report that includes implementation steps, resource requirements, and expected effects.

[0127] In this specific implementation, this step is the real-time data acquisition and decision support stage. During this stage, it is necessary to collect real-time transportation data and energy consumption data from road, waterway, and rail transport, as well as logistics storage. This real-time data, after undergoing the same preprocessing steps as before, is input into the corresponding accounting sub-model.

[0128] After the sub-model is run, carbon emission results for each route can be obtained. Analysis of these results allows for the selection of the optimal carbon emission route. Based on this optimal route, a detailed decision support report can be generated. This report not only includes the implementation steps of the optimal route but also lists the required resources and expected effects. For example, the report might recommend increasing freight volume on a specific route because it performs best in terms of carbon emissions; or it might recommend changing to a different mode of transportation because its carbon emission factor is lower and can effectively reduce total carbon emissions.

[0129] This decision support report provides clear and specific guidance for decision-makers in port and shipping container transportation, helping them to minimize carbon emissions while meeting transportation needs, thus contributing to the company's sustainable development and environmental protection.

[0130] In this embodiment, by implementing the carbon emission accounting method for port and shipping container transportation, multi-source data can be collected and processed comprehensively and accurately, a dynamically updated carbon factor parameter library can be constructed, and dedicated accounting sub-models can be established for different modes of transportation to achieve precise quantification of carbon emissions throughout the transportation process. Combining optimization algorithms and machine learning techniques, this method can select the optimal carbon emission path, providing a scientific basis for transportation decisions. Model calibration and verification ensure the accuracy and reliability of the accounting results. Ultimately, through real-time data collection and decision support, the transformation of port and shipping container transportation towards low-carbon and high-efficiency goals can be promoted, achieving multiple objectives such as reducing carbon emissions, saving costs, and enhancing corporate competitiveness and environmental benefits.

[0131] like Figure 2 As shown, the following are embodiments of the carbon emission accounting system for port and shipping container transportation provided in this disclosure. This system and the carbon emission accounting methods for port and shipping container transportation in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the carbon emission accounting system for port and shipping container transportation, please refer to the embodiments of the carbon emission accounting methods for port and shipping container transportation described above.

[0132] A carbon emission accounting system for port and shipping container transportation includes:

[0133] The multi-source data acquisition and preprocessing module is used to collect transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage in a classified manner. After preprocessing, the data is classified and stored to form a standardized dataset.

[0134] The carbon factor parameter library construction module is used to create a parameter library containing various carbon emission factors according to industry standards and in combination with different modes of transportation and cargo types, and to establish a dynamic update mechanism that analyzes historical data through machine learning algorithms and updates various carbon emission factors regularly.

[0135] The intelligent accounting model construction module is used to build accounting sub-models for different modes of transportation such as road, waterway, and railway. Each accounting sub-model uses corresponding formulas and parameters to calculate carbon emissions based on the characteristics and data of the specific mode of transportation.

[0136] The model training and optimization module is used to input standardized datasets into the corresponding sub-models, calculate carbon emissions, and select the optimal carbon emission pathways.

[0137] The model calibration and validation module is used to calibrate the sub-model using multiple sets of historical data and adjust the model parameters.

[0138] The model execution module is used to collect real-time transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage. After preprocessing, the data is input into the corresponding accounting sub-model. The accounting sub-model is run to obtain carbon emission results for each path, select the optimal carbon emission path, and generate a decision support report that includes implementation steps, resource requirements, and expected effects.

[0139] The carbon emission accounting system for port and shipping container transportation provided in this embodiment achieves accurate quantification of carbon emissions throughout the entire transportation process by accurately collecting and processing multi-source data, constructing a dynamically updated carbon factor parameter library, and developing dedicated accounting sub-models for different modes of transportation. By combining optimization algorithms and machine learning techniques to select the optimal path, it not only significantly improves the accuracy and reliability of carbon emission accounting but also provides scientific support for transportation decisions, effectively promoting the transformation of the port and shipping transportation industry towards low-carbon and high-efficiency operations, and achieving a win-win situation for both environmental and economic benefits.

[0140] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0141] The carbon emission accounting method for port and shipping container transportation provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0142] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0143] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0144] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0145] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0146] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0147] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0148] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0149] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0150] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0151] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0152] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0153] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0154] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0155] The aforementioned electronic equipment realizes the carbon emission accounting method for port and shipping container transportation in this application. It collects and preprocesses data from road, waterway, and rail transportation and logistics storage links, constructs a dynamically updated carbon emission factor parameter library, establishes dedicated accounting sub-models for different modes of transportation, and uses optimization and machine learning algorithms to select the optimal carbon emission path. This achieves the beneficial effects of accurately quantifying carbon emissions, optimizing transportation decisions, reducing carbon emission costs, improving economic benefits and corporate competitiveness, and realizing the green and low-carbon transformation of port and shipping container transportation.

[0156] The storage medium provided in this application stores a program product capable of implementing a carbon emission accounting method for port and shipping container transportation processes.

[0157] Methods for calculating carbon emissions during container shipping include:

[0158] Transportation data and energy consumption data from road, waterway, and rail transportation and logistics storage are collected in categories, preprocessed, and then stored in categories to form a standardized dataset.

[0159] In accordance with industry standards, and taking into account different modes of transportation and types of goods, a parameter library containing various carbon emission factors was created, and a dynamic update mechanism was established. Historical data was analyzed through machine learning algorithms, and various carbon emission factors were updated regularly.

[0160] For each mode of transportation—road, waterway, and rail—a separate accounting sub-model is constructed. Each sub-model is used to calculate carbon emissions based on the characteristics and data of the specific mode of transportation, employing appropriate formulas and parameters.

[0161] The standardized dataset is input into the corresponding accounting sub-model to calculate carbon emissions and select the optimal carbon emission path.

[0162] The sub-model was calibrated using multiple sets of historical data, and the model parameters were adjusted.

[0163] Real-time data collection of transportation and energy consumption data from highway, waterway, and railway transportation and logistics storage is conducted. After preprocessing, the data is input into the corresponding accounting sub-model. The accounting sub-model is then run to obtain carbon emission results for each route, select the optimal carbon emission route, and generate a decision support report that includes implementation steps, resource requirements, and expected effects.

[0164] In some possible implementations, the carbon emission accounting method for container shipping processes disclosed herein can be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0165] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0166] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for carbon emission accounting in port and shipping container transportation, characterized in that, include: Transportation data and energy consumption data from road, waterway, and rail transportation and logistics storage are collected in categories, preprocessed, and then stored in categories to form a standardized dataset. In accordance with industry standards, and taking into account different modes of transportation and types of goods, a parameter library containing various carbon emission factors was created, and a dynamic update mechanism was established. Historical data was analyzed through machine learning algorithms, and various carbon emission factors were updated regularly. For each mode of transportation—road, waterway, and rail—a separate accounting sub-model is constructed. Each sub-model is used to calculate carbon emissions based on the characteristics and data of the specific mode of transportation, employing appropriate formulas and parameters. The standardized dataset is input into the corresponding accounting sub-model to calculate carbon emissions and select the optimal carbon emission path. The sub-model was calibrated using multiple sets of historical data, and the model parameters were adjusted. Real-time collection of transportation data and energy consumption data from road, waterway, and rail transportation and logistics storage links; after preprocessing, input into the corresponding accounting sub-model; run the accounting sub-model to obtain carbon emission results for each path; select the optimal carbon emission path; and generate a decision support report that includes implementation steps, resource requirements, and expected effects. The data collected in the categorized manner, including transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage, are preprocessed and then categorized and stored to form a standardized dataset, including: Collect transportation data and energy consumption data in the road transportation process, including vehicle fuel supply type, refrigerant filling table for cold boxes, average vehicle fuel consumption, and route information; Collect transportation data and energy consumption data in the waterway transportation process, including ship fuel supply type, refrigerant filling table for cold boxes, average ship fuel consumption, and route information; Collect transportation data and energy consumption data in the railway transportation process, including train fuel supply type, refrigerant filling table for cold boxes, average train fuel consumption, and route information; Collect transportation and energy consumption data in the logistics and storage process, including energy consumption of ships at port and shore power usage of ships at port; Collect information on transportation methods, historical carbon emission data, and related environmental data; For the collected data, a cleaning process is performed to remove outliers and fill in missing values. Data units and formats are standardized, and the data is classified and stored according to different links and data types in the cargo transportation process to form a standardized dataset. For the transportation modes of highway, waterway, and railway, separate accounting sub-models are constructed, including: For road, waterway, and rail transportation modes, carbon accounting operator models are constructed for road transportation, logistics and storage, waterway transportation, and rail transportation, respectively. The road transport carbon accounting sub-model uses the mileage method to calculate carbon dioxide emissions, including: In the formula, Croad,i represents the carbon dioxide emissions of the i-th type of vehicle, Ffuel consumption,i represents the average fuel consumption per unit of the i-th type of vehicle, Efuel,i represents the greenhouse gas emission factor of the fuel used by the vehicle, Cemission,j represents the direct greenhouse gas emissions of the j-th type of emission source, and Ti represents the freight turnover of the i-th type of vehicle. The calculation formula is Ti = Wi × Di, where Wi is the weight of the goods and Di is the transport distance. For refrigerated container transportation, the emissions from fugitive sources are calculated using the following formula: Where Rj is the amount of the j-th refrigerant added, PGWP,j is the global warming potential of the j-th escaping source, and Kecaping,j is the escaping coefficient of the j-th escaping source. The logistics storage carbon accounting sub-model includes a loading and unloading operation carbon accounting model and a cold storage carbon accounting model; The carbon accounting model for loading and unloading operations includes: Wherein, Cloading represents the greenhouse gas emissions from loading and unloading operations, Cfuel,k represents the average fuel consumption of the k-th type of loading and unloading equipment, Ffuel consumption,k represents the unit fuel consumption of the k-th type of loading and unloading equipment, and Efuel,k represents the greenhouse gas emission factor of the fuel used by the loading and unloading equipment. The carbon accounting models for refrigerated storage include: Wherein, Crefrigeration represents the direct greenhouse gas emissions during the refrigeration storage process, Rl represents the amount of refrigerant added to the refrigeration equipment, PGWP,l represents the global warming potential of the refrigerant, and Kemission,l represents the emission coefficient of the refrigerant. The waterway transportation carbon accounting sub-model includes a navigation process carbon accounting model and a port berthing process carbon accounting model; The carbon accounting model for navigation includes: Wherein, C_waterway,m represents the carbon dioxide emissions of the m-th type of vessel, T_m represents the cargo turnover of the m-th type of vessel, F_fuel consumption,m represents the fuel consumption per ton-kilometer of the m-th type of vessel, E_fuel,m represents the greenhouse gas emission factor of the fuel used by the vessel, and C_emission,n represents the direct greenhouse gas emissions of the n-th emission source. The carbon accounting model for the berthing process includes: When ships use shore power When the ship is not using shore power, ; Wherein, C berthing represents the greenhouse gas emissions during the berthing process, E shore power represents the shore power usage during the ship's berthing period, E electricity represents the greenhouse gas emission factor of electricity, to represents the berthing duration, Po represents the power of the ship's auxiliary machinery, and E fuel oil,o represents the greenhouse gas emission factor of the ship's fuel oil. The emission reductions from replacing fuel oil with shore power can be calculated using the following formula: Where Rsubstitution represents the reduction in carbon dioxide emissions by using shore power instead of fuel oil, Bp represents the unit fuel consumption rate of the ship's diesel generator, and Efuel,p represents the greenhouse gas emission factor of the ship's fuel oil.

2. The carbon emission accounting method for port and shipping container transportation according to claim 1, characterized in that, The railway transportation carbon accounting sub-model includes a diesel locomotive carbon accounting model and an electrified railway carbon accounting model; The carbon accounting model for internal combustion locomotives includes: Wherein, Crailway,q represents the greenhouse gas emissions of the diesel locomotive, Vq represents the estimated consumption of the q-th type of fuel in the locomotive, Ffuel consumption,q represents the fuel consumption rate of the locomotive, Efuel,q represents the greenhouse gas emission factor of the fuel, and Esupply,q represents the greenhouse gas emission factor of the fuel supply process. The carbon accounting model for electrified railways includes: Wherein, Celectric,r represents the greenhouse gas emissions of electrified railway locomotives, Vr represents the estimated power consumption of the r-th type of locomotive, and Eelectric,r represents the greenhouse gas emission factor of purchased electricity.

3. The carbon emission accounting method for port and shipping container transportation according to claim 2, characterized in that, The process of inputting a standardized dataset into the corresponding accounting sub-model to calculate carbon emissions and select the optimal carbon emission pathway includes: The standardized dataset is input into the corresponding sub-model. First, the objective function and constraints are determined using linear programming, nonlinear programming, or dynamic programming optimization methods. The preliminary optimal carbon emission path is obtained by solving for the optimal solution. Then, machine learning algorithms are used to train the model on historical data so that the model can predict the carbon emission results of different paths. The optimal carbon emission path is then selected from the preliminary optimal carbon emission path.

4. The carbon emission accounting method for port and shipping container transportation according to claim 3, characterized in that, The calibration of the sub-model using multiple sets of historical data and the adjustment of model parameters include: The accounting sub-model is calibrated using multiple sets of historical data. The carbon emissions simulated by the accounting sub-model for a certain period in the past are compared with the actual carbon emissions. If the difference in carbon emissions exceeds a preset threshold, the relevant parameters are adjusted. The accuracy of the accounting sub-model's prediction of future carbon emissions is verified by using reserved historical data or cited research data. If the verification fails, the model parameters are adjusted.

5. A carbon emission accounting system for port and shipping container transportation, characterized in that, The system adopts the carbon emission accounting method for port and shipping container transportation as described in any one of claims 1 to 4; The system includes: The multi-source data acquisition and preprocessing module is used to collect transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage in a classified manner. After preprocessing, the data is classified and stored to form a standardized dataset. The carbon factor parameter library construction module is used to create a parameter library containing various carbon emission factors according to industry standards and in combination with different modes of transportation and cargo types, and to establish a dynamic update mechanism. It analyzes historical data through machine learning algorithms and updates various carbon emission factors regularly. The intelligent accounting model construction module is used to build accounting sub-models for different modes of transportation such as road, waterway, and railway. Each accounting sub-model is used to calculate carbon emissions based on the characteristics and data of the specific mode of transportation, using corresponding formulas and parameters. The model training and optimization module is used to input standardized datasets into the corresponding sub-models, calculate carbon emissions, and select the optimal carbon emission pathways. The model calibration and validation module is used to calibrate the sub-model using multiple sets of historical data and adjust the model parameters. The model execution module is used to collect real-time transportation data and energy consumption data from highway, waterway, and railway transportation and logistics storage. After preprocessing, the data is input into the corresponding accounting sub-model. The accounting sub-model is run to obtain carbon emission results for each path, select the optimal carbon emission path, and generate a decision support report that includes implementation steps, resource requirements, and expected effects.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the carbon emission accounting method for port and shipping container transportation as described in any one of claims 1 to 4.

7. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the carbon emission accounting method for port and shipping container transportation as described in any one of claims 1 to 4.

Images