Method and system for constructing process-level steel product life cycle carbon footprint model

Abstract

This invention relates to the field of carbon footprint model construction technology, providing a method and system for constructing a process-level carbon footprint model for the entire life cycle of steel products. The method includes dynamically adjusting and verifying the basic boundaries of the process levels for steel products; determining the dynamic data quality requirements and dynamic emission factor system for carbon emissions based on the full life cycle stages of steel products and the dynamically verified basic boundaries of the process levels, thereby constructing a three-level life cycle inventory of stages, processes, and nodes; constructing a dynamic calculation model for process-level carbon footprint data that incorporates multi-dimensional dynamic deduction logic; forming a dynamically updated dataset of core influencing factors; and using the trained full life cycle carbon footprint model for real-time carbon footprint calculation, dynamic management, and node traceability. This enables accurate carbon footprint calculation and node traceability, improving the authenticity and accuracy of the calculation results and providing precise support for the optimization of low-carbon processes in steel enterprises.

Description

Technical Field

[0001] This invention relates to the field of carbon footprint modeling technology, and in particular to a method and system for constructing a process-level carbon footprint model of steel products throughout their entire life cycle. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Existing carbon footprint models for steel products often use fixed process boundaries, failing to consider the impact of process adjustments (such as changes in scrap steel ratios and blast furnace conditions) and fluctuations in operating conditions (such as load changes) on these boundaries. The entire lifecycle is disconnected from the process level, and the carbon emission deduction logic is incomplete. This makes it difficult to adapt to different process routes such as blast furnace-converter and electric arc furnace short processes, as well as the dynamic needs of different production stages within the same enterprise. The carbon footprint nodes cannot be traced, and the calculation results may deviate from actual production scenarios, failing to guide actual process improvements for steel products. Summary of the Invention

[0004] To address the aforementioned technical issues, this invention provides a method and system for constructing a carbon footprint model of steel products across their entire lifecycle at the process level. This model enables accurate calculation and traceability of carbon footprints, improves the authenticity and accuracy of the calculation results, and provides precise support for optimizing low-carbon processes in steel enterprises.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of this invention provides a method for constructing a carbon footprint model of the entire life cycle of steel products at the process level.

[0006] In one or more embodiments, a method for constructing a process-level steel product lifecycle carbon footprint model is provided, including: Based on the process type, production conditions and accounting accuracy requirements of steel products, the basic boundaries of the process level of steel products are dynamically adjusted and dynamically verified in combination with the preset boundary dynamic adjustment rules. Based on the entire life cycle stages of steel products and the basic boundaries of the process level for dynamic verification, the quality requirements for dynamic carbon emission data and the dynamic emission factor system are determined, and a three-level life cycle list of stage-process-node is constructed. Based on a three-level lifecycle inventory of stage-process-node, and combined with the technological mechanism of steel products, a dynamic calculation model for carbon footprint data at the process level is constructed, which incorporates multi-dimensional dynamic deduction logic. Based on the dynamic calculation model and dynamic contribution rate algorithm of carbon footprint data at the process level, the contribution rate of each activity data at each node to the total carbon footprint of steel products is calculated, thereby determining the activity data belonging to the core influencing factors. Combined with the experience of steel industry experts, a dynamically updated dataset of core influencing factors is formed. Based on the dynamically updated dataset of core influencing factors and their corresponding carbon footprints, a sample set is formed, and then the initial full life cycle carbon footprint model is trained until the training ends at the preset requirements. The trained full life cycle carbon footprint model is used for real-time carbon footprint calculation, dynamic management and control and node traceability.

[0007] As one implementation method, the dynamic calculation model for the carbon footprint data at the process level is as follows:

[0008] In the formula: The carbon footprint of steel products throughout their entire lifecycle; Carbon emissions during the raw material acquisition stage; Carbon emissions during the distribution and transportation phase; Carbon emissions during the end-of-life disposal phase; The dynamic deduction amount for recycled raw materials at the end of their life cycle is dynamically calculated based on the amount of recycled raw materials used and differences in emission factors. Let J represent the carbon emissions of the j-th process.

[0009] As one implementation method, the carbon emissions of the j-th process for:

[0010] in, This refers to the amount of cross-process resource recovered in the j-th process; Let z be the emission factor corresponding to the z-th type of cross-process resource recovery; The deduction coefficient for the z-th type of cross-process recycled resource in the j-th process; z is the code for the type of cross-process recycled resource; j is the process code, 1=sintering, 2=ironmaking, 3=steelmaking, 4=steel rolling; Let be the carbon emissions of the k-th node; This is the total node of the j-th process.

[0011] As one implementation method, the carbon emissions of the k-th node for:

[0012] In the formula: This represents the m-th type of activity data for the k-th node; The dynamic emission factor corresponding to the m-th type of activity data at the k-th node; This is the operating condition adjustment coefficient for the k-th node; The amount of resource to be recycled at the k-th node is the w-th type. Let w be the emission factor corresponding to the w-th type of recyclable resource; is the dynamic deduction coefficient for the w-th type of recycled resource at the k-th node; m is the code for the activity data type; w is the code for the type of recycled resource; k is the node code.

[0013] As one implementation method, the boundary dynamic adjustment rule is as follows: Process adaptation and adjustment: For the blast furnace-converter process, the boundaries of ironmaking and steelmaking processes are expanded to include the generation and reuse nodes of blast furnace gas and converter gas; for the electric arc furnace short-process process, the boundaries of sintering process are simplified and the boundary coverage of scrap steel pretreatment and electric arc furnace smelting is strengthened. Operating condition adaptation adjustment: When the production load fluctuates, the selection rules for each process are adjusted to ignore emission sources with a contribution of less than 0.5% to the carbon footprint; when the load is normal, the selection rules are restored to those with a contribution of less than 1%. Precision adaptation adjustment: If high-precision calculation is required, refine the boundaries of sub-nodes in each process; if rapid calculation is required, merge some related sub-nodes and simplify boundary division.

[0014] As one implementation method, the dynamic emission factor system includes: Fossil fuel emission factors: Enterprise measured values ​​are preferred; if no measured values ​​are available, industry default values ​​are used, and the values ​​are dynamically adjusted according to fuel type and combustion efficiency. Raw material emission factors: Dynamically matched according to raw material type, origin, and processing technology to clarify the difference in emission factors between recycled raw materials and virgin raw materials, for subsequent dynamic deduction; Process-specific emission factors: Set specific emission factors for the core nodes of each process to improve the accuracy of process-level accounting; Dynamic update mechanism: Emission factors are updated according to preset time intervals by combining updates to external carbon accounting standards and industry information.

[0015] As one implementation method, the method for constructing a carbon footprint model of steel products throughout their entire life cycle at the process level also includes: Establish a dynamic update mechanism for the full life cycle carbon footprint model. Update the parameters, emission factor system, and core influencing factor dataset of the full life cycle carbon footprint model according to a preset cycle, combining industry update data, carbon accounting standard updates, and enterprise production data feedback, to ensure that the model always adapts to actual production needs and industry standards.

[0016] A second aspect of the present invention provides a system for constructing a carbon footprint model of the entire life cycle of steel products at the process level.

[0017] In one or more embodiments, a process-level steel product lifecycle carbon footprint model construction system includes: The boundary dynamic adjustment and verification module is used to dynamically adjust and verify the basic boundaries of the process level of steel products based on the process type, production conditions and accounting accuracy requirements of steel products, combined with preset boundary dynamic adjustment rules. The three-level life cycle inventory construction module is used to determine the carbon emission dynamic data quality requirements and dynamic emission factor system based on the full life cycle stages of steel products and the basic boundaries of the process level of dynamic verification, and then construct a three-level life cycle inventory of stage-process-node. The carbon footprint data dynamic calculation model construction module is used to construct a process-level carbon footprint data dynamic calculation model that incorporates multi-dimensional dynamic deduction logic based on the three-level life cycle inventory of stage-process-node and combined with the process mechanism of steel products. The core influencing factors dataset dynamic update module is used to calculate the contribution rate of each activity data at each node to the total carbon footprint of steel products based on the dynamic calculation model and dynamic contribution rate algorithm of carbon footprint data at the process level, thereby determining the activity data belonging to the core influencing factors, and then combining the experience of steel industry experts to form a dynamically updated core influencing factors dataset. The full life cycle carbon footprint model training module is used to form a sample set based on the dynamically updated dataset of core influencing factors and their corresponding carbon footprints, and then train the initial full life cycle carbon footprint model until the training ends at the preset requirements. The trained full life cycle carbon footprint model is then used for real-time carbon footprint calculation, dynamic management and control and node traceability.

[0018] A third aspect of the present invention provides a computer-readable storage medium.

[0019] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the process-level steel product lifecycle carbon footprint model construction method described above.

[0020] A fourth aspect of the present invention provides an electronic device.

[0021] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the process-level steel product lifecycle carbon footprint model construction method described above.

[0022] Compared with the prior art, the beneficial effects of the present invention are: This invention dynamically adjusts the basic boundaries of the process hierarchy of steel products based on the process type, production conditions, and accounting accuracy requirements of steel products. This adapts to the dynamic changes in different process routes and production conditions. Combined with a dynamic emission factor system, it forms a three-level lifecycle inventory of stages, processes, and nodes, achieving deep integration of each stage and process level throughout the entire lifecycle. This leads to the construction of a dynamic calculation model for process-level carbon footprint data that incorporates multi-dimensional dynamic deduction logic. This improves the carbon emission deduction logic, enabling dynamic deduction of energy reuse, material recycling, and recycled raw materials between processes. Finally, the initial full lifecycle carbon footprint model is trained using a dynamically updated dataset of core influencing factors. The trained full lifecycle carbon footprint model is then used for real-time carbon footprint accounting, dynamic management, and node traceability, improving the authenticity and accuracy of the accounting results and providing precise support for the optimization of low-carbon processes in steel enterprises. Attached Figure Description

[0023] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0024] Figure 1 This is a flowchart of the method for constructing a carbon footprint model of steel products throughout their entire life cycle at the process level, according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the process-level steel product full life cycle carbon footprint model construction system according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0025] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0027] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0028] Existing carbon footprint models for steel products do not deeply bind each stage of the entire life cycle (raw materials, production, transportation, and end-of-life treatment) to the process level, making it impossible to achieve node-based traceability and precise control of the carbon footprint. These models also fail to fully consider the dynamic deductions for energy reuse between steel production processes (such as the cross-process reuse of blast furnace gas and coke oven gas), material recycling (such as the recovery and reuse of slag and dust), and the differences in carbon emissions between recycled and primary raw materials. Therefore, the calculation results may deviate from actual production scenarios. This invention aims to propose a method and system for constructing a carbon footprint model of the entire life cycle of steel products at the process level. It constructs a dynamically adjustable process-level accounting boundary to adapt to the dynamic changes of different process routes and production conditions, solving the problems of rigid boundaries and poor adaptability in existing models. It achieves deep integration of each stage of the entire life cycle with the process level, establishing a three-level accounting system of "stage-process-node," enabling accurate carbon footprint accounting and node traceability. It also improves the carbon emission deduction logic, realizing dynamic deductions for energy reuse, material recycling, and recycled raw materials between processes, enhancing the authenticity and accuracy of the accounting results, and providing precise support for the optimization of low-carbon processes in steel enterprises.

[0029] Figure 1 A flowchart of the method for constructing a process-level steel product lifecycle carbon footprint model according to an embodiment of the present invention is provided. Figure 1 The method for constructing a process-level steel product lifecycle carbon footprint model in this embodiment may include the following steps S101 to S105.

[0030] The specific implementation process of steps S101 to S105 is as follows: Step S101: Based on the process type, production conditions and accounting accuracy requirements of steel products, and combined with the preset boundary dynamic adjustment rules, dynamically adjust the basic boundary of the process level of steel products, and perform dynamic verification.

[0031] In the specific implementation process, the target steel products are defined. Based on the actual needs of steel enterprises for carbon control, product carbon certification, and low-carbon process optimization, the target products of the model are clarified, including specific steel products (such as hot-rolled coils, cold-rolled steel plates, and structural steel) and similar product groups (such as structural steel for construction and steel plates for automobiles), covering different process routes such as blast furnace-converter and electric arc furnace short process.

[0032] Combining steel industry practices and carbon accounting standards, the "ton of product" (t) is uniformly adopted as the functional unit to calculate the carbon footprint of each ton of steel product throughout its entire life cycle, with the unit being ton CO2 equivalent (tCO2e), ensuring the comparability of carbon footprints for different products and different companies.

[0033] Define the model's computational accuracy requirements (goodness of fit ≥ 0.96), applicable scenarios (different processes, different production scales), and dynamic adjustment requirements (boundary adaptation when operating conditions change or processes are adjusted), so as to provide a basis for subsequent boundary division and model construction.

[0034] Specifically, the life cycle is divided into four core stages: raw material acquisition, production and manufacturing, distribution and transportation, and end-of-life disposal, covering the entire boundary from "cradle to grave". This can be flexibly configured according to actual accounting needs (such as only accounting for the production process).

[0035] Basic boundary definition of process level: Taking the production and manufacturing stage as the core, the basic boundaries of the four core processes of sintering, ironmaking, steelmaking and rolling are defined, and the core inputs (raw materials, energy) and outputs (intermediate products, carbon emissions, recycled resources) of each process are clearly defined to avoid data overlap between processes; at the same time, the connection boundary between each stage and process is clearly defined (e.g., the end point of the raw material stage is that the raw materials enter the sintering / ironmaking process, and the end point of the production stage is that the finished steel leaves the factory).

[0036] In the specific implementation process, based on the process type, production conditions, and accounting accuracy requirements, dynamic boundary adjustment rules are established, as follows: (1) Process adaptation and adjustment: For the blast furnace-converter process, the focus is on expanding the boundaries of the ironmaking and steelmaking processes and incorporating the generation and reuse nodes of blast furnace gas and converter gas; for the electric arc furnace short process, the boundaries of the sintering process are simplified and the boundary coverage of scrap steel pretreatment and electric arc furnace smelting is strengthened. (2) Working condition adaptation adjustment: When the production load fluctuates (e.g., the load is below 70%), the selection rules of each process are adjusted to ignore emission sources with a carbon footprint contribution of <0.5% (e.g., a small amount of auxiliary material consumption); when the load is normal, the selection rules are restored to the contribution of <1%. (3) Precision adaptation adjustment: If high-precision calculation is required (such as product carbon certification), refine the boundaries of sub-nodes of each process (such as the ironmaking process being subdivided into sub-nodes such as blast furnace feeding, smelting, and tapping); if rapid calculation is required (such as enterprise daily management and control), merge some related sub-nodes and simplify boundary division.

[0037] During the dynamic boundary verification process, a boundary verification model is established. By comparing the carbon footprint accounting results under different boundary settings and combining them with the actual measurement data of enterprises, the rationality of the boundary adjustment is verified, ensuring that the dynamic boundary is both adapted to actual production and does not affect the accounting accuracy.

[0038] This embodiment innovatively proposes a dynamic boundary mechanism for process levels, breaking through the limitations of existing fixed boundaries, realizing adaptive adaptation to different processes and working conditions, solving the core pain points of poor adaptability and rigid boundaries in existing models, and significantly improving model adaptability.

[0039] Step S102: Based on the entire life cycle stages of steel products and the basic boundaries of the process level for dynamic verification, determine the quality requirements for dynamic carbon emission data and the dynamic emission factor system, and then construct a three-level life cycle list of stage-process-node.

[0040] Priority should be given to using real-time process-level data measured by the enterprise (such as hourly energy consumption and material consumption data), followed by industry standard data and database data; for dynamic boundary adjustments, a data adaptation mechanism should be established to automatically match the data collection range and quality standards of the corresponding process and node when the boundary is adjusted; the data must be traceable, and the original measurement ledgers and test reports should be retained to ensure authenticity, accuracy and completeness.

[0041] For data shared between processes (such as public electricity and steam) and data shared across stages, a dynamic allocation principle will be established, which will differ from the existing fixed allocation ratio: (1) Public energy allocation: dynamically allocated according to the real-time energy consumption ratio of each process, and the allocation ratio is updated once per shift; (2) Allocation of recycled resources: The carbon emission deduction of recycled energy (such as blast furnace gas) and recycled materials is dynamically allocated according to the actual reuse ratio of each process; (3) By-product allocation: The carbon emission deduction ratio is dynamically adjusted according to the real-time output and carbon content of by-products.

[0042] Specifically, the dynamic emission factor system includes: (1) Fossil fuel emission factor: Enterprise measured values ​​are preferred. If no measured values ​​are available, the industry default values ​​are used and dynamically adjusted according to fuel type (such as coke, pulverized coal) and combustion efficiency. (2) Raw material emission factors: Dynamically match the emission factors of recycled raw materials (primary iron ore, recycled scrap steel), origin and processing technology to clarify the differences between the emission factors of primary raw materials and recycled raw materials, which will be used for subsequent dynamic deduction; (3) Process-specific emission factors: Set specific emission factors for core nodes of each process (such as sintering ignition node and blast furnace smelting node) to improve the accuracy of process-level accounting; (4) Dynamic update mechanism: The emission factor database is updated quarterly in conjunction with carbon accounting standard updates and industry update data to ensure the timeliness and adaptability of the factors.

[0043] This embodiment establishes a dynamic carbon emission deduction system and data update mechanism, improves the deduction logic for recycled resources and recycled raw materials, and makes the calculation results more consistent with the actual steel production, with the error controlled within ±3%, providing a reliable basis for product carbon certification and enterprise low-carbon management.

[0044] The three-level lifecycle checklist of stage-process-node includes: Level 1 List (Phase-level): Based on the four phases of raw material acquisition, production and manufacturing, distribution and transportation, and end-of-life disposal, a phase-level list is compiled, which includes the overall input and output data of each phase and clarifies the connection between each phase and the process.

[0045] Secondary inventory (process level): Based on the four core processes of sintering, ironmaking, steelmaking and rolling, process-level inventory is compiled. Combined with dynamic boundaries, the material consumption, energy consumption, direct emissions, and recycled resources of each process are statistically analyzed, as well as the corresponding emission factors, to ensure that the inventory data is accurately matched with the dynamic boundaries.

[0046] Level 3 Inventory (Node Level): For the core nodes of each process (such as the mixing, ignition, and cooling nodes in the sintering process; and the feeding, smelting, and tapping nodes in the ironmaking process), a node-level inventory is compiled, and real-time activity data at the node level (such as fuel consumption at the ignition node and furnace temperature data at the smelting node) is collected to achieve accurate traceability of carbon footprint.

[0047] Dynamic inventory update: Establish a dynamic inventory update mechanism. When dynamic boundaries are adjusted or production conditions change, the inventory data at the corresponding level and node will be automatically updated to ensure that the inventory matches the actual production scenario in real time.

[0048] This embodiment constructs a three-level lifecycle list of "stage-process-node" to achieve deep integration of the entire lifecycle and the process level, solving the problems of the existing model's disconnect between the entire lifecycle and the process and weak traceability. It can accurately locate key carbon emission nodes and provide precise support for low-carbon optimization.

[0049] Step S103: Based on the three-level lifecycle list of stage-process-node and combined with the technological mechanism of steel products, construct a dynamic calculation model of carbon footprint data at the process level that incorporates multi-dimensional dynamic deduction logic.

[0050] For each core node of the process, a dynamic calculation formula is constructed based on the process mechanism, considering the impact of changes in node operating conditions on carbon emissions: Carbon emissions at the k-th node. (Unit: tCO2e, tons of carbon dioxide equivalent) is:

[0051] In the formula: For the m-th activity data of the k-th node (material consumption, energy consumption, units: t, MWh, etc.); The dynamic emission factor corresponding to the m-th type of activity data at the k-th node; The operating condition adjustment coefficient for the k-th node (dynamically determined based on operating conditions such as production load and furnace temperature, ranging from 0.8 to 1.2). For the w-th type of resource recovery at the k-th node (recovered energy, recovered materials, units: t, 10), ...4 (Nm³, etc.) Let w be the emission factor corresponding to the w-th type of recyclable resource; is the dynamic deduction coefficient for the w-th type of recycled resource at the k-th node (dynamically determined based on the reuse ratio and recycling efficiency, ranging from 0.6 to 1.0); m is the code for the activity data type; w is the code for the type of recycled resource; and k is the node code.

[0052] By summing the carbon emissions of all nodes in each process and combining them with the deduction of recycled resources between processes, we can obtain the process-level carbon emissions, specifically the carbon emissions of the j-th process. (Unit: tCO2e) is:

[0053] in, This refers to the amount of cross-process resource recovered in the j-th process; Let z be the emission factor corresponding to the z-th type of cross-process resource recovery; The deduction coefficient for the z-th type of cross-process recycled resource in the j-th process; z is the code for the type of cross-process recycled resource; j is the process code, 1=sintering, 2=ironmaking, 3=steelmaking, 4=steel rolling; Let be the carbon emissions of the k-th node; This is the total node of the j-th process.

[0054] Specifically, the dynamic calculation model for carbon footprint data at the process level is as follows:

[0055] In the formula: The carbon footprint of steel products throughout their entire life cycle (unit: tCO2e / t product). Carbon emissions during the raw material acquisition stage (unit: tCO2e); Carbon emissions during the distribution and transportation phase; (unit: tCO2e) Carbon emissions during the end-of-life treatment phase (unit: tCO2e). The dynamic deduction amount for recycled raw materials at the end of their life cycle (in tCO2e) is dynamically calculated based on the amount of recycled raw materials used and differences in emission factors. The carbon emissions of the j-th process are expressed in tCO2e.

[0056] Step S104: Based on the dynamic calculation model and dynamic contribution rate algorithm of carbon footprint data at the process level, calculate the contribution rate of each activity data at each node to the total carbon footprint of steel products, and then determine the activity data belonging to the core influencing factors. Combined with the experience of steel industry experts, a dynamically updated dataset of core influencing factors is formed.

[0057] By combining dynamic boundaries and three-level inventory data, the core influencing factors are dynamically identified, as follows: Sample collection: Steel enterprises with different process routes (blast furnace-converter, electric arc furnace short process), different production scales, and different operating conditions were selected to collect multiple sets of third-level inventory data and carbon footprint accounting results for target products to ensure the diversity and representativeness of the samples.

[0058] Contribution rate calculation: A dynamic contribution rate algorithm is used to calculate the contribution rate of each node and activity data (material consumption, energy consumption, process parameters) to the total carbon footprint of the product. The formula is as follows:

[0059] In the formula: The dynamic contribution rate (%) of the data for the i-th activity of the j-th product; This is the data for the i-th activity of the j-th product; The dynamic emission factor corresponding to the i-th activity data of the j-th product; This is the working condition adjustment coefficient corresponding to the i-th activity data of the j-th product; The total lifecycle carbon footprint of the j-th product is calculated using the dynamic calculation model of carbon footprint data at the process level described above.

[0060] Dynamic filtering: The data of each activity are sorted from high to low according to the dynamic contribution rate. The data of the activities with a total contribution rate of 85% are taken as the core influencing factors. At the same time, the experience of steel industry experts is combined to supplement key characteristic factors such as process parameters (such as blast furnace temperature and scrap steel ratio) and operating conditions (such as production load) to form a dynamically updated set of core influencing factors (the core influencing factors are automatically updated when the process and operating conditions change).

[0061] Step S105: Based on the dynamically updated dataset of core influencing factors and their corresponding carbon footprints, a sample set is formed, and then the initial full life cycle carbon footprint model is trained until the training ends at the preset requirements. The trained full life cycle carbon footprint model is used for real-time carbon footprint calculation, dynamic management and control and node traceability.

[0062] In some alternative embodiments, the initial life-cycle carbon footprint model can be constructed by integrating process mechanisms and advanced machine learning algorithms to balance physical plausibility and prediction accuracy. The hybrid model consists of three parts: a process mechanism module, an attention mechanism-LSTM module, and a fusion output layer. The specific structure is as follows: (1) Process mechanism module: Based on the physical and chemical reaction laws of each process in steel production (such as iron ore reduction reaction and fuel combustion reaction), a basic accounting model is constructed, the core influencing factor data is input, and the preliminary carbon footprint prediction results are output to ensure the physical rationality of the model and avoid the "black box" problem of machine learning algorithms. (2) Attention Mechanism - LSTM Module: Receives the preliminary prediction results and core influencing factor data from the process mechanism module. The attention mechanism is used to focus on the process nodes and activity data that have the greatest impact on carbon footprint. The LSTM module is used to capture the time-series dynamic changes of core influencing factors (such as the time-series fluctuations of furnace temperature and energy consumption) and the nonlinear correlation between processes, and outputs the time-series correction coefficient. (3) Fusion output layer: The preliminary prediction results of the process mechanism module are fused with the timing correction coefficients of the attention mechanism-LSTM module to output the final carbon footprint prediction results, taking into account both physical rationality and prediction accuracy.

[0063] Model parameter settings: (1) Process mechanism module: Based on the steel production process formula, parameters such as reaction efficiency and energy consumption coefficient are set and can be dynamically adjusted according to different process routes; (2) Attention mechanism - LSTM module: The number of neurons in the input layer is the core influencing factor, and the number of neurons in the hidden layer is determined by an empirical formula. Where b is the number of input layer nodes, c is the number of output layer nodes, and a is an integer between 1 and 10), the time step is set to 12 (to adapt to daily time series data of steel production), the learning rate is set to 0.001, the number of iterations is 60, and the Adam optimization algorithm is used. (3) Fusion output layer: The weighted fusion method is adopted, with the weight of the process mechanism module result set to 0.6 and the weight of the attention mechanism-LSTM module correction coefficient set to 0.4, to ensure that the model takes into account both physical rationality and prediction accuracy.

[0064] Model training: The acquired sample data is divided into a training set (80%) and a test set (20%), and input into the hybrid model for training. The carbon footprint calculation result is used as the target value, and the model parameters are iteratively updated until the model converges (mean squared error MSE < 0.0008).

[0065] The "three-dimensional verification method" is adopted, namely accuracy verification, adaptability verification, and dynamic verification, to comprehensively verify the model performance. (1) Accuracy verification: The goodness of fit of the model (R²) is calculated using the test set data. The requirement is that R² ≥ 0.96. At the same time, the model prediction results are compared with the actual measured data of the enterprise, and the error is controlled within ±3%. (2) Adaptability verification: The model is applied to steel enterprises with different process routes and different production scales to verify the model's adaptability to dynamic boundaries and ensure that the calculation accuracy in different scenarios meets the requirements. (3) Dynamic verification: Simulate changes in production conditions and process adjustments to verify the model’s response speed and adaptation accuracy to boundary adjustments and updates of core influencing factors, ensuring that the model can keep up with production changes in real time.

[0066] Targeted optimization measures were taken to address the errors that occurred during the verification process: (1) If the accuracy is not up to standard, adjust the parameters of the attention mechanism-LSTM module (such as the number of hidden layer neurons and the learning rate) and retrain the model; (2) If the adaptability is insufficient, optimize the dynamic boundary adjustment mechanism and emission factor system to enhance the model's scenario adaptability; (3) If the dynamic response is lagging, simplify the model calculation process, optimize the data update mechanism, and improve the model response speed; (4) In conjunction with the updating of carbon accounting standards, regularly optimize the model structure and calculation logic to ensure the timeliness of the model.

[0067] The optimized hybrid model is embedded into the steel enterprise's production management system to collect process-level and node-level data in real time, enabling real-time calculation, dynamic control, and node traceability of carbon footprint. At the same time, it provides personalized adaptation functions, allowing enterprises to adjust dynamic boundaries and core parameters according to their own processes and operating conditions without having to remodel.

[0068] It should be noted that in other embodiments, the network topology of the full life cycle carbon footprint model can also be implemented using other existing neural network structures, which will not be described in detail here.

[0069] This embodiment is technically feasible, as it can obtain the required data by relying on the company's existing metering ledgers and production management systems without requiring any new technological breakthroughs. It can be quickly implemented in steel companies, reducing the company's modeling and carbon management costs, and has extremely high industrial application value. It is compatible with mainstream carbon accounting standards and can dynamically optimize the model according to the standards, providing technical support for the standardization and normalization of carbon footprint accounting in the steel industry.

[0070] In one or more embodiments, the method for constructing a process-level steel product lifecycle carbon footprint model further includes: Establish a dynamic update mechanism for the full life cycle carbon footprint model. Update the parameters, emission factor system, and core influencing factor dataset of the full life cycle carbon footprint model according to a preset cycle, combining industry update data, carbon accounting standard updates, and enterprise production data feedback, to ensure that the model always adapts to actual production needs and industry standards.

[0071] like Figure 2 As shown, the process-level steel product lifecycle carbon footprint model construction system provided in this embodiment of the invention can be implemented in software. The process-level steel product lifecycle carbon footprint model construction system includes the following software modules: Boundary dynamic adjustment and verification module 201 is used to dynamically adjust the basic boundary of the process level of steel products based on the process type, production conditions and accounting accuracy requirements of steel products, combined with preset boundary dynamic adjustment rules, and to perform dynamic verification. The three-level life cycle inventory construction module 202 is used to determine the carbon emission dynamic data quality requirements and dynamic emission factor system based on the full life cycle stages of steel products and the basic boundaries of the process level of dynamic verification, and then construct a three-level life cycle inventory of stage-process-node. The carbon footprint data dynamic calculation model construction module 203 is used to construct a process-level carbon footprint data dynamic calculation model based on a three-level life cycle inventory of stage-process-node and combined with the process mechanism of steel products, incorporating multi-dimensional dynamic deduction logic. The core influencing factor dataset dynamic update module 204 is used to calculate the contribution rate of each activity data at each node to the total carbon footprint of steel products based on the dynamic calculation model and dynamic contribution rate algorithm of carbon footprint data at the process level, thereby determining the activity data belonging to the core influencing factors, and then combining the experience of steel industry experts to form a dynamically updated core influencing factor dataset. The full life cycle carbon footprint model training module 205 is used to form a sample set based on the dynamically updated core influencing factor dataset and its corresponding carbon footprint, and then train the initial full life cycle carbon footprint model until the training ends at the preset requirements. The trained full life cycle carbon footprint model is then used for real-time carbon footprint calculation, dynamic management and control and node traceability.

[0072] It should be noted that each module in the process-level steel product life-cycle carbon footprint model construction system of this invention corresponds one-to-one with each step in the process-level steel product life-cycle carbon footprint model construction method in the above embodiments, and their specific implementation processes are the same, so they will not be repeated here.

[0073] The structure of the electronic device according to an embodiment of the present invention will be described in detail below. Figure 3 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention. It can be understood that... Figure 3 The diagram shows only an exemplary structure of the electronic device, not the entire structure. Some or all of the structures shown may be implemented as needed.

[0074] The electronic device provided in this embodiment of the invention includes: at least one processor 301, a memory 302, a user interface 303, and at least one network interface 304. The various components in the process-level steel product lifecycle carbon footprint model construction system are coupled together via a bus system 305. It can be understood that the bus system 305 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 305 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 3 The general designated all buses as Bus System 305.

[0075] The user interface 303 may include a monitor, keyboard, mouse, trackball, click wheel, buttons, touchpad, or touch screen.

[0076] It is understood that memory 302 can be volatile memory or non-volatile memory, or both. In this embodiment of the invention, memory 302 is capable of storing data to support the operation of the terminal. Examples of this data include any computer programs used to operate on the terminal, such as operating systems and applications. The operating system includes various system programs, such as framework layers, core library layers, driver layers, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications.

[0077] In some embodiments, the process-level steel product lifecycle carbon footprint model construction system provided in this invention can be implemented using a combination of hardware and software. For example, the process-level steel product lifecycle carbon footprint model construction system provided in this invention can be a processor in the form of a hardware decoding processor, programmed to execute the process-level steel product lifecycle carbon footprint model construction method provided in this invention. For instance, the hardware decoding processor can employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0078] As an example, processor 301 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0079] As an example of the hardware implementation of the process-level steel product lifecycle carbon footprint model construction system provided in this embodiment of the invention, the device provided in this embodiment of the invention can be directly executed by a processor 301 in the form of a hardware decoding processor. For example, it can be executed by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components to implement the process-level steel product lifecycle carbon footprint model construction method provided in this embodiment of the invention.

[0080] In this embodiment of the invention, the memory 302 is used to store various types of data to support the operation of the process-level steel product full life cycle carbon footprint model construction system, or to store data for execution. Figure 1 The program code for the method shown. Examples of this data include: any executable instructions for operating on a process-level steel product lifecycle carbon footprint modeling system, such as executable instructions that can be included in the executable instructions, implementing the process-level steel product lifecycle carbon footprint modeling method of this embodiment.

[0081] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including functions for executing... Figure 1 The program code for the method shown. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by the central processing unit, it performs the various functions defined in the apparatus of this application.

[0082] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for constructing a carbon footprint model of the entire life cycle of steel products at the process level, characterized in that, include: Based on the process type, production conditions and accounting accuracy requirements of steel products, the basic boundaries of the process level of steel products are dynamically adjusted and dynamically verified in combination with the preset boundary dynamic adjustment rules. Based on the entire life cycle stages of steel products and the basic boundaries of the process level for dynamic verification, the quality requirements for dynamic carbon emission data and the dynamic emission factor system are determined, and a three-level life cycle list of stage-process-node is constructed. Based on a three-level lifecycle inventory of stages, processes, and nodes, and combined with the technological mechanism of steel products, a dynamic calculation model for carbon footprint data at the process level is constructed, which incorporates multi-dimensional dynamic deduction logic. Based on the dynamic calculation model and dynamic contribution rate algorithm of carbon footprint data at the process level, the contribution rate of each activity data at each node to the total carbon footprint of steel products is calculated, thereby determining the activity data belonging to the core influencing factors. Combined with the experience of steel industry experts, a dynamically updated dataset of core influencing factors is formed. Based on the dynamically updated dataset of core influencing factors and their corresponding carbon footprints, a sample set is formed, and then the initial full life cycle carbon footprint model is trained until the training ends at the preset requirements. The trained full life cycle carbon footprint model is used for real-time carbon footprint calculation, dynamic management and control and node traceability.

2. The method for constructing a process-level steel product lifecycle carbon footprint model as described in claim 1, characterized in that, The dynamic calculation model for the carbon footprint data at the process level is as follows: In the formula: The carbon footprint of steel products throughout their entire lifecycle; Carbon emissions during the raw material acquisition stage; Carbon emissions during the distribution and transportation phase; Carbon emissions during the end-of-life disposal phase; The dynamic deduction amount for recycled raw materials at the end of their life cycle is dynamically calculated based on the amount of recycled raw materials used and differences in emission factors. Let J represent the carbon emissions of the j-th process.

3. The method for constructing a process-level steel product lifecycle carbon footprint model as described in claim 2, characterized in that, Carbon emissions of the j-th process for: in, This refers to the amount of cross-process resource recovered in the j-th process; Let z be the emission factor corresponding to the z-th type of cross-process resource recovery; The deduction coefficient for the z-th type of cross-process recycled resource in the j-th process; z is the code for the type of cross-process recycled resource; j is the process code, 1=sintering, 2=ironmaking, 3=steelmaking, 4=steel rolling; Let be the carbon emissions of the k-th node; This is the total node of the j-th process.

4. The method for constructing a process-level steel product lifecycle carbon footprint model as described in claim 3, characterized in that, Carbon emissions at the kth node for: In the formula: This represents the m-th type of activity data for the k-th node; The dynamic emission factor corresponding to the m-th type of activity data at the k-th node; This is the operating condition adjustment coefficient for the k-th node; The amount of resource to be recycled at the k-th node is the w-th type. Let w be the emission factor corresponding to the w-th type of recyclable resource; is the dynamic deduction coefficient for the w-th type of recycled resource at the k-th node; m is the code for the activity data type; w is the code for the type of recycled resource; k is the node code.

5. The method for constructing a process-level steel product lifecycle carbon footprint model as described in claim 1, characterized in that, The boundary dynamic adjustment rules are as follows: Process adaptation and adjustment: For the blast furnace-converter process, the boundaries of ironmaking and steelmaking processes are expanded to include the generation and reuse nodes of blast furnace gas and converter gas; for the electric arc furnace short-process process, the boundaries of sintering process are simplified and the boundary coverage of scrap steel pretreatment and electric arc furnace smelting is strengthened. Operating condition adaptation adjustment: When the production load fluctuates, the selection rules for each process are adjusted to ignore emission sources with a contribution of less than 0.5% to the carbon footprint; when the load is normal, the selection rules are restored to those with a contribution of less than 1%. Precision adaptation adjustment: If high-precision calculation is required, refine the boundaries of sub-nodes in each process; if rapid calculation is required, merge some related sub-nodes and simplify boundary division.

6. The method for constructing a process-level steel product lifecycle carbon footprint model as described in claim 1, characterized in that, The dynamic emission factor system includes: Fossil fuel emission factors: Enterprise measured values ​​are preferred; if no measured values ​​are available, industry default values ​​are used, and the values ​​are dynamically adjusted according to fuel type and combustion efficiency. Raw material emission factors: Dynamically matched according to raw material type, origin, and processing technology to clarify the difference in emission factors between recycled raw materials and virgin raw materials, for subsequent dynamic deduction; Process-specific emission factors: Set specific emission factors for the core nodes of each process to improve the accuracy of process-level accounting; Dynamic update mechanism: Emission factors are updated according to preset time intervals by combining updates to external carbon accounting standards and industry information.

7. The method for constructing a process-level steel product lifecycle carbon footprint model as described in claim 1, characterized in that, Also includes: Establish a dynamic update mechanism for the full life cycle carbon footprint model. Update the parameters, emission factor system, and core influencing factor dataset of the full life cycle carbon footprint model according to a preset cycle, combining industry update data, carbon accounting standard updates, and enterprise production data feedback, to ensure that the model always adapts to actual production needs and industry standards.

8. A system for constructing a carbon footprint model of the entire life cycle of steel products at the process level, characterized in that, The method for constructing a process-level steel product lifecycle carbon footprint model based on any one of claims 1-7 includes: The boundary dynamic adjustment and verification module is used to dynamically adjust and verify the basic boundaries of the process level of steel products based on the process type, production conditions and accounting accuracy requirements of steel products, combined with preset boundary dynamic adjustment rules. The three-level life cycle inventory construction module is used to determine the carbon emission dynamic data quality requirements and dynamic emission factor system based on the full life cycle stages of steel products and the basic boundaries of the process level of dynamic verification, and then construct a three-level life cycle inventory of stage-process-node. The carbon footprint data dynamic calculation model construction module is used to construct a process-level carbon footprint data dynamic calculation model that incorporates multi-dimensional dynamic deduction logic based on the three-level life cycle inventory of stage-process-node and combined with the process mechanism of steel products. The core influencing factors dataset dynamic update module is used to calculate the contribution rate of each activity data at each node to the total carbon footprint of steel products based on the dynamic calculation model and dynamic contribution rate algorithm of carbon footprint data at the process level, thereby determining the activity data belonging to the core influencing factors, and then combining the experience of steel industry experts to form a dynamically updated core influencing factors dataset. The full life cycle carbon footprint model training module is used to form a sample set based on the dynamically updated dataset of core influencing factors and their corresponding carbon footprints, and then train the initial full life cycle carbon footprint model until the training ends at the preset requirements. The trained full life cycle carbon footprint model is then used for real-time carbon footprint calculation, dynamic management and control and node traceability.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the method for constructing a process-level steel product lifecycle carbon footprint model as described in any one of claims 1-7.

10. 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 in the method for constructing a carbon footprint model of the entire life cycle of steel products at the process level as described in any one of claims 1-7.

Images