Carbon emission prediction method and device for special steel
By receiving and analyzing user request information, determining and adjusting target submodules and parameters in the production process of special steel, the accurate prediction of carbon emissions in the production process of special steel is achieved, and the problem of inaccurate evaluation in the existing technology is solved. Flexible and accurate assessment capabilities.
Patent Information
- Application Number
- CN202410955794.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-17
AI Technical Summary
The existing carbon emission assessment method in the steel industry is difficult to accurately and flexibly respond to customized needs in the production process of special steel, especially when facing a variety of different raw materials and processes, which leads to inaccurate carbon emission forecasts. .
By receiving the target request information input by the user, analyzing the process flow information, determining the target submodule and initial input parameters, adjusting the parameters to obtain the updated input parameters, and then conducting carbon emission prediction, adopting modular design and association adjustment to achieve more Accurate evaluation.
It provides more flexible and accurate carbon emission assessment capabilities, can accurately predict specific links and needs, and is suitable for customized production processes of special steels.
Smart Images

Figure CN118504785B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of carbon emission prediction, and in particular to a method and device for predicting carbon emission of special steel. Background Art
[0002] As global climate change and sustainable development issues become increasingly prominent, the carbon emissions of the steel industry, as one of the world's largest carbon emission sources, have received widespread attention. At present, the carbon emission assessment methods of the steel industry mainly rely on empirical models, which usually require professional system developers to process and integrate data, which is not conducive to direct operation and understanding by business departments. In the existing life cycle assessment methods, data collection and processing are usually cumbersome.
[0003] Special steel production often needs to be customized according to the specific needs of customers, which means that the production process and the choice of raw materials can vary greatly. Existing life cycle assessment methods are usually designed for standardized and conventional production processes. Special steel production involves a variety of different raw materials and processes. When dealing with these complex variables, existing life cycle assessment methods cannot fully capture and reflect the impact between various links, especially when faced with carbon emission forecasts under such highly customized needs, it is often difficult to provide flexible and accurate assessments. Summary of the invention
[0004] The present invention provides a carbon emission prediction method and device for special steel, which are used to solve the defect in the prior art that it is impossible to accurately and flexibly respond to the user's carbon emission prediction request for a specific link, and to achieve the effect of providing a more flexible and accurate evaluation.
[0005] The present invention provides a method for predicting carbon emissions of special steel, comprising:
[0006] Receive target request information input by the user;
[0007] Parsing the target request information to identify process flow information associated with the life cycle of special steel;
[0008] Based on the process information, a target submodule and initial input parameters of the target submodule are determined from the special steel carbon emission life cycle model; the target submodule includes interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the special steel production process, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transmission and calculation of the target data in the target unit;
[0009] Based on the process flow information and the target submodule, determining an associated submodule that has interaction or data transmission with the target submodule;
[0010] Based on the initial input parameter and the association relationship between the target submodule and the association submodule, the initial input parameter is adjusted to obtain an updated target input parameter;
[0011] The target input parameters are input into the target submodule to obtain the carbon emission prediction result output by the target submodule.
[0012] According to a carbon emission prediction method for special steel provided by the present invention, the association relationship includes an input-output relationship, and the input-output relationship is used to determine the transmission relationship of data between different submodules; based on the initial input parameter and the association relationship between the target submodule and the association submodule, the initial input parameter is adjusted to obtain the updated target input parameter, including:
[0013] Determining the associated parameters of each associated submodule based on the initial input parameters and the associated relationship between the target submodule and the associated submodule; the associated parameters include parameters output by each associated submodule to the target submodule, or parameters output by the target submodule to each associated submodule;
[0014] When the parameters output by the associating submodule to the target submodule do not meet the requirements of the target submodule, or when the parameters output by the target submodule to the associating submodule do not meet the requirements of the associating submodule, the initial input parameters are adjusted to obtain updated target input parameters.
[0015] According to a carbon emission prediction method for special steel provided by the present invention, the association relationship also includes data dependency relationship, time relationship, resource relationship, spatial relationship, quality relationship and economic relationship; the data dependency relationship is used to indicate the consistency or coordination of data between sub-modules; the time relationship is used to indicate that each sub-module performs calculation and data transmission in a set time series; the resource relationship is used to indicate the sharing and competition relationship of each sub-module for resources, so as to realize the allocation of resources among different sub-modules; the spatial relationship is used to indicate the layout relationship of each sub-module in physical space; the quality relationship is used to indicate the relationship between the quality of the output of each sub-module and the input quality of the sub-module; the economic relationship is used to indicate the cost and benefit relationship of each sub-module.
[0016] According to a carbon emission prediction method for special steel provided by the present invention, the target input parameter is input into the target submodule to obtain the carbon emission prediction result output by the target submodule, including:
[0017] Using the target input parameters as input data for each target unit;
[0018] Based on the target logic, the allocation ratio of each parameter among the target units and the carbon emission calculation rules of each target unit are determined to obtain the carbon emission prediction results of each target unit.
[0019] According to a carbon emission prediction method for special steel provided by the present invention, the process links of the process flow information include at least one of sintering, coking, blast furnace, electric furnace, ironmaking, steelmaking, continuous casting, die casting, and rolling.
[0020] According to a carbon emission prediction method for special steel provided by the present invention, the target data includes at least one of raw material data, auxiliary material data, energy data, product data, by-product data, atmospheric emission data, water emission data, and solid waste data.
[0021] According to a carbon emission prediction method for special steel provided by the present invention, the carbon emission life cycle model of special steel is established by the following steps:
[0022] Collecting input and output data of each process flow, and matching the input and output data with the target data;
[0023] The carbon dioxide emissions of the next target unit of each process are cumulatively calculated according to the functional unit, and matched to the corresponding submodule of each process in the special steel carbon emission life cycle model;
[0024] The special steel carbon emission life cycle model is verified through iron balance calculation, mass balance calculation and sensitivity analysis to obtain the special steel carbon emission life cycle model.
[0025] The present invention also provides a carbon emission prediction device for special steel, comprising:
[0026] A receiving module, used for receiving target request information input by a user;
[0027] A parsing module, used to parse the target request information and identify process flow information associated with the life cycle of special steel;
[0028] A first processing module is used to determine a target submodule and initial input parameters of the target submodule from a special steel carbon emission life cycle model based on the process flow information; the target submodule includes interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the special steel production process, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transfer and calculation of the target data in the target unit;
[0029] A second processing module, configured to determine, based on the process information and the target submodule, an associated submodule that interacts with or transfers data to the target submodule;
[0030] A parameter updating module, configured to adjust the initial input parameters based on the initial input parameters and the association relationship between the target submodule and the association submodule to obtain updated target input parameters;
[0031] The prediction module is used to input the target input parameters into the target submodule to obtain the carbon emission prediction result output by the target submodule.
[0032] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a carbon emission prediction method for special steel as described in any one of the above-mentioned methods is implemented.
[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the carbon emission prediction method for special steel as described in any one of the above.
[0034] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for predicting carbon emissions of special steel.
[0035] The carbon emission prediction method and device for special steel provided by the present invention receive target request information input by the user, identify the process flow information associated with the life cycle of special steel, and then obtain the initial input parameters of the model, the target sub-module, and the associated sub-module that interacts or transmits data with the target sub-module, thereby realizing modular data output capability, and then the initial input parameters can be adjusted according to the associated relationship to obtain updated target input parameters, and more accurate input parameters for specific links and specific target sub-modules can be determined according to customized needs, thereby obtaining the carbon emission prediction results output by the target sub-module, providing more flexible and accurate evaluation. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0037] Figure 1 This is one of the flow diagrams of the carbon emission prediction method for special steel provided by the present invention;
[0038] Figure 2 This is the second flow chart of the carbon emission prediction method for special steel provided by the present invention;
[0039] Figure 3 It is a structural schematic diagram of a carbon emission prediction device for special steel provided by the present invention;
[0040] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0042] Combine the following Figure 1-Figure 4 The carbon emission prediction method and device of special steel of the present invention are described.
[0043] like Figure 1 As shown, the carbon emission prediction method for special steel according to an embodiment of the present invention mainly includes step 110, step 120, step 130, step 140, step 150 and step 160.
[0044] Step 110: receiving target request information input by a user.
[0045] It is understood that a target driver can be used to capture the target request information input by the user. This request information includes a query, prediction or analysis of carbon emissions in the production process of special steel. The target driver can be designed to handle various types of user input, including but not limited to queries submitted through the user interface, regular requests from automated systems, or data calls from third-party systems.
[0046] The target driver can capture the target request information input by the user through the user interface, API interface or automated system. For example, the user can enter a request through the interface to query the carbon emissions generated by a specific batch of special steel in a certain production link.
[0047] Step 120, parse the target request information to identify process flow information associated with the life cycle of special steel.
[0048] The process information related to the life cycle of special steel can be extracted from the analysis results. The process information can include target system, target unit, target data and target logic, which correspond to different stages and production processes in the production process of special steel.
[0049] In this case, the logical analyzer intervenes and conducts in-depth analysis of the target request information submitted by the user. The parsing process includes syntax analysis and semantic analysis to ensure that the model can not only identify the user's query intent, but also accurately understand the user's specific needs.
[0050] For example, parse the user's target request information and identify the production stages involved in the request, such as blast furnace, rolling, etc.
[0051] Step 130, based on the process information, determine the target submodule and the initial input parameters of the target submodule from the special steel carbon emission life cycle model.
[0052] It can be understood that after obtaining the parsed process flow information, the result of the analysis is a set of target systems, target units, target data, and target logic. This information corresponds to different stages and different production processes of the special steel production process involved in the user request.
[0053] The target submodule includes interrelated target data, target unit and target logic; the target data is used to represent various types of data involved in the special steel production process, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transmission and calculation of target data in the target unit.
[0054] The target data covers all kinds of data involved in the production process, such as raw materials, energy, emissions, etc. The target unit represents the various equipment and process units used in production; the target logic is used to connect and coordinate the transmission and calculation of the target data in the target unit. Through this modular design, the system can flexibly organize and process production data, accurately transmit and calculate data in each link, so as to systematically calculate and predict carbon emissions in the production process, and improve the accuracy and efficiency of the assessment.
[0055] The target data includes at least one of raw material data, auxiliary material data, energy data, product data, by-product data, air emission data, water emission data, and solid waste data.
[0056] Target logic is a structured system that is used to connect and coordinate the transmission and calculation of target data in the target unit. Target logic ensures accurate data transmission and calculation by setting product codes, target data categories, target data codes, and the allocation ratio, numerator-denominator relationship, and calculation rules of each data item. Specifically, the various parts of target logic are described as follows.
[0057] The product code is used to uniquely identify a specific product produced. Each product code corresponds to a specific special steel product.
[0058] The target data categories represent different classifications of data, such as raw materials, auxiliary materials, energy, products, by-products, air emissions, water emissions, solid waste, etc. Each type of data represents a different aspect of the production process.
[0059] The target data code is used to further subdivide the target data category and specifically identify the specific items in a certain category of data, for example, different types of iron ore under the raw materials category or coal gas and natural gas under the energy category.
[0060] In the production process, various raw materials and energy may be used by multiple products or process stages. The allocation ratio of each data item is used to reasonably allocate these data to each product or process stage. For example, if a blast furnace provides molten iron for multiple production lines at the same time, the amount of molten iron used needs to be allocated according to the needs of each production line.
[0061] The numerator-denominator relationship is used to express the ratio or proportional relationship that needs to be used when calculating carbon emissions. For example, the carbon emissions corresponding to each unit of raw materials can be expressed as the ratio of the amount of raw materials used (numerator) to the amount of products produced (denominator).
[0062] Calculation rules are specific formulas and methods used to convert data such as raw materials and energy into carbon emissions data. These rules are based on industry standards and scientific research to ensure the accuracy and consistency of the calculation results.
[0063] Through target logic, a large amount of production data can be effectively managed and processed, so that various data can be accurately transmitted and calculated in the carbon emission prediction model, thereby improving the efficiency and accuracy of the entire evaluation process. For example, in actual operation, target logic can help the system automatically identify and process data input and output at different process stages, ensuring that the calculation of carbon emissions can reflect the actual production process.
[0064] The target units refer to various equipment and process units used in production, including but not limited to cold rolling and acid rolling units, galvanizing units, three-sintering operation area, plate flat sintering machine, power generation-CDQ power generation, plate hot rolling unit-hot rolled pattern coil, gas-coke oven gas, plate flat sintering machine and coking operation area, etc. These units are responsible for different process steps in the production process, involving the processing of raw materials, energy consumption, product manufacturing, and the processing of by-products and wastes. Through the collaboration of various links, a complete production chain is formed.
[0065] The process links of process flow information include at least one of sintering, coking, blast furnace, electric furnace, ironmaking, steelmaking, continuous casting, die casting, and rolling. Each process link corresponds to specific target data, target logic, and target unit. The input and output data in these links directly affect the carbon emissions of the entire special steel production life cycle. Through detailed analysis and data collection of these process links, the carbon emission sources of each stage can be accurately determined, accurate sub-modules can be obtained, and comprehensive carbon emission assessment results can be obtained through model calculation.
[0066] Step 140 , based on the process flow information and the target submodule, determine the associated submodules that interact or transfer data with the target submodule.
[0067] Based on the process information and the target submodule, the system will determine the associated submodules that interact or transfer data with the target submodule. Specifically, the target submodule will contain specific production links and related data, which may affect or depend on the data of other submodules.
[0068] For example, the output data of the steelmaking submodule will affect the input data of the continuous casting submodule; similarly, the output data of the continuous casting submodule will affect the input data of the subsequent steel rolling submodule. In this way, the system can identify all associated submodules that have an interactive or data transfer relationship with the target submodule, thereby ensuring that the data transfer and calculation in the entire life cycle model are accurate and coherent.
[0069] Step 150: Based on the initial input parameters and the association relationship between the target submodule and the associated submodule, the initial input parameters are adjusted to obtain updated target input parameters.
[0070] The initial input parameters can be adjusted to ensure that the data transfer and conversion between modules are accurate and consistent, and then the updated target input parameters are obtained, thereby ensuring that the input and output data of all stages in the entire production process can accurately reflect the actual situation.
[0071] By analyzing the data interaction and transmission relationship between the target submodule and the associated submodules in detail, the source, target and transmission method of the data, as well as the format, unit and accuracy requirements of the data can be determined.
[0072] In this process, the key parameters that affect the accuracy of data interaction and transmission are determined, and the key parameters are determined based on the association relationship. Based on the analysis of the key parameters, the initial input parameters of the association submodule are adjusted to ensure the accuracy and consistency of data interaction and transmission.
[0073] Step 160, input the target input parameters into the target submodule to obtain the carbon emission prediction result output by the target submodule.
[0074] Input the target input parameters into the target submodule to perform carbon emission prediction and obtain the prediction results.
[0075] The processed data can be encapsulated in the format requested by the user through the result converter to generate the results required by the user, and then fed back to the user through the front end, ensuring that the information obtained by the user is intuitive and easy to understand.
[0076] In this embodiment, the submodule adopts a modular data processing method, by decomposing the life cycle model into multiple submodules, each of which targets a specific stage in the production process. This modular design makes data processing more flexible and efficient, and also facilitates optimization and updating for specific stages.
[0077] In the process of specific application, ensure that each sub-module has a clearly defined interface for data transmission and interaction, which can ensure the collaboration and data fluency between different sub-modules.
[0078] Each submodule is designed with appropriate functions and tasks to ensure that it can effectively process the data and task requirements of a specific stage. The designed functions in the submodule are implemented as independent modules, which can be software modules, algorithm modules, data processing flows, etc. The specific form depends on the requirements.
[0079] On this basis, the various sub-modules are integrated to ensure that they can work together and produce the expected results. Based on actual applications and feedback, the various sub-modules can be optimized and updated.
[0080] In some embodiments, the target input parameters are input into the target submodule to obtain the carbon emission prediction results output by the target submodule, including: using the target input parameters as input data for each target unit; based on the target logic, determining the allocation ratio of each parameter among the target units and the carbon emission calculation rules for each target unit to obtain the carbon emission prediction results for each target unit.
[0081] The target input parameters are used as input data for each target unit, that is, the input parameters are allocated to different units or equipment, so as to perform a forecast calculation of carbon emissions for each unit.
[0082] By determining the allocation ratio and carbon emission calculation rules based on the target logic, we can determine the allocation ratio of each parameter among the target units, as well as how to calculate the carbon emissions of each unit based on these parameters, taking into full account factors such as energy utilization efficiency, output differences, and equipment characteristics among units.
[0083] According to the above-mentioned apportionment ratio and calculation rules, the carbon emission forecast calculation can be performed on each target unit to obtain the carbon emission forecast result of each target unit, and then the data can be summarized and organized to obtain the carbon emission forecast result output by the target submodule.
[0084] According to an embodiment of the present invention, a carbon emission prediction method for special steel is provided. By receiving target request information input by a user, process flow information associated with the life cycle of the special steel is identified, and then the initial input parameters of the model, the target sub-module, and the associated sub-module that interacts or transfers data with the target sub-module are obtained, thereby realizing modular data output capability. The initial input parameters can be adjusted according to the associated relationship to obtain updated target input parameters, and more accurate input parameters for specific links and specific target sub-modules can be determined according to customized needs, thereby obtaining the carbon emission prediction results output by the target sub-module, providing a more flexible and accurate evaluation.
[0085] In some embodiments, the association relationship includes an input-output relationship, and the input-output relationship is used to determine the data transmission relationship between different sub-modules.
[0086] like Figure 2 As shown, based on the initial input parameters and the association relationship between the target submodule and the associated submodule, the initial input parameters are adjusted to obtain updated target input parameters, including step 151 and step 152.
[0087] Step 151 : determining the association parameters of each associated submodule based on the initial input parameters and the association relationship between the target submodule and the associated submodule.
[0088] Step 152, when the parameters output from the associated submodule to the target submodule do not meet the requirements of the target submodule, or when the parameters output from the target submodule to the associated submodule do not meet the requirements of the associated submodule, adjust the initial input parameters to obtain updated target input parameters.
[0089] The association relationship refers to the association or connection between sub-modules, which can be expressed in the form of input-output relationship. The input-output relationship is used to determine how data is transferred and exchanged between different sub-modules.
[0090] The associated parameters include parameters output by each associated submodule to the target submodule, or parameters output by the target submodule to each associated submodule.
[0091] For example, the output parameter types of the ironmaking submodule include molten iron, and the input parameter types include iron ore, coke, and other auxiliary materials. In the steelmaking submodule, the input parameter types include molten iron (provided by the ironmaking submodule), scrap steel, and alloy materials.
[0092] In this embodiment, by fully considering the data transmission relationship between different sub-modules and adjusting the initial input parameters, more accurate input data can be obtained, thereby ensuring the accuracy of the target sub-module prediction.
[0093] In some embodiments, the association relationship also includes data dependency relationship, time relationship, resource relationship, spatial relationship, quality relationship and economic relationship.
[0094] Data dependency is used to indicate the consistency or coordination of data between sub-modules. Data dependency means that the data items of one module depend on the data items of another module. This dependency ensures the consistency and accuracy of data between modules.
[0095] For example, for the input-output relationship listed above, the amount of hot metal in the steelmaking submodule also depends on the hot metal output of the ironmaking submodule. The hot metal output of the ironmaking submodule determines the hot metal input of the steelmaking submodule. If the ironmaking submodule outputs 1,000 tons of hot metal, then the hot metal input of the steelmaking submodule should also be 1,000 tons (taking into account losses and other adjustments).
[0096] For example, the amount of hot metal input to the steelmaking submodule depends not only on the hot metal output of the ironmaking submodule, but also on the ratio of raw materials. For example, if a specific type of special steel is to be produced, the ratio of iron ore to scrap steel needs to be controlled in the raw materials. If the raw material ratio is 1:1, that is, the amount of iron carried by each ton of iron ore is equal to the amount of iron carried by each ton of scrap steel, then the amount of hot metal input to the steelmaking submodule will be determined according to this ratio.
[0097] The time relationship is used to indicate that each submodule performs calculations and data transfers in a set time sequence. The time relationship refers to the time sequence and impact of each stage in the production process. This relationship ensures that each module performs calculations and data transfers in a reasonable time sequence.
[0098] For example, the ironmaking submodule must be completed before the steelmaking submodule, because steelmaking requires the output of ironmaking. The cold rolling mill is after the hot rolling mill, because hot rolling is a prerequisite for cold rolling.
[0099] Resource relations are used to represent the sharing and competition relationship of resources among submodules, so as to realize the allocation of resources among different submodules. This relationship ensures the reasonable allocation and utilization of resources among different modules, avoiding resource conflicts and waste.
[0100] For example, energy resources such as electricity and gas are allocated between different modules. Another example is that some equipment may be shared in different production stages, and the use time and sequence of the equipment need to be coordinated.
[0101] Spatial relationship is used to represent the layout relationship of each sub-module in the physical space. Spatial relationship refers to the layout and mutual influence of the target units in each sub-module in the physical space. This relationship helps to optimize the logistics and equipment layout in the production process and improve production efficiency.
[0102] For example, when laying out a production line, consider the impact of the physical location arrangement of production links such as steelmaking and steel rolling. In addition, consider the impact of the spatial arrangement between different equipment. These spatial relationships will affect the specific progress of the process and the accuracy of the input data.
[0103] The quality relationship is used to express the relationship between the quality of the output of each submodule and the quality of the input of the submodule. This relationship ensures the consistency and control of product quality during the production process.
[0104] For example, the purity of molten steel in the steelmaking submodule directly affects the product quality of the steel rolling submodule. The pickling effect of the cold rolling pickling mill affects the galvanizing quality of the subsequent process. When considering the input of the subsequent submodule, the impact of product quality on the subsequent product process is taken into account, thereby affecting the accuracy of data input.
[0105] Economic relationships are used to represent the cost and benefit relationships of each submodule, which helps to consider economic benefits and cost control in carbon emission forecasts.
[0106] For example, production costs affect the cost accounting of energy consumption, raw material usage, etc. of different submodules. Profit represents the output value and economic benefits in the production process. Different economic relationships affect the cost accounting of energy consumption, raw material usage, etc. and the value of output, which in turn affects the accuracy of the input parameters.
[0107] In order to realize the above-mentioned input-output relationship and data dependency, it is necessary to set the specific relationship between the target submodule and the associated submodule in detail.
[0108] When making carbon emission predictions, it is necessary to adjust the initial input parameters according to the association between the target submodule and the associated submodule to ensure the accuracy and rationality of the prediction.
[0109] It can be understood that the accurate transmission and conversion of data can be achieved based on the specific relationship between the target sub-module and the associated sub-module, and through the input-output relationship and data dependency, thereby ensuring the accuracy of the parameters input into the model, ensuring the accuracy of carbon emission forecasts at each stage, and improving the flexibility and response speed of the system.
[0110] In some embodiments, a special steel carbon emission life cycle model is established through the following steps.
[0111] You can first collect the input and output data of each process flow and match the input and output data with the target data.
[0112] It is understandable that it is necessary to collect input and output data in each process flow, which may include raw material usage, energy consumption, product output, etc. Then match these input and output data with the set target parameters to determine which data is associated with the target parameters.
[0113] Then, the carbon dioxide emissions of the next target unit of each process are cumulatively calculated according to the functional units and matched to the corresponding sub-modules of each process in the special steel carbon emission life cycle model.
[0114] The CO2 emissions of the target unit under each process flow are calculated cumulatively according to functional units (e.g. per ton of special steel produced), i.e. the calculation process of converting input and output data into carbon emissions, taking into account the contribution of different process flows to carbon emissions.
[0115] The calculated carbon emissions are matched with the corresponding submodules in the special steel carbon emission life cycle model, so that the carbon emission data of each process flow can be integrated into the corresponding part of the model.
[0116] Finally, the carbon emission life cycle model of special steel was verified through iron balance accounting, mass balance accounting and sensitivity analysis to obtain a verified carbon emission life cycle model of special steel.
[0117] Through iron balance accounting, accurate material accounting is performed on the input and output of iron ore, molten iron and other materials in the ironmaking process to ensure the accuracy of material balance. Mass balance accounting focuses on the mass ratio of input and output of each process of galvanized products. The reliability of the model is verified by calculating the results of process mass balance accounting. Sensitivity analysis is performed on input data and assumed variables. By running the Tornado Chart tool, the input parameters that have the greatest impact on the life cycle assessment results are identified, thereby evaluating the uncertainty of the model and the sensitivity of the data.
[0118] The special steel carbon emission life cycle model is verified through iron balance accounting (ensuring the balance between iron input and output), mass balance accounting (ensuring the balance between product quality and output) and sensitivity analysis (sensitivity testing of model parameters and input data) to ensure the accuracy and reliability of the model.
[0119] Taking into account the uncertainties in the special steel carbon emission life cycle model, such as the accuracy of inventory data and the assumptions of the evaluation and analysis model, uncertainty analysis is performed by setting the input parameters to follow a normal distribution to determine and quantify the impact of the accumulation of uncertainty and data changes on the results. The uncertainty analysis results of special steel bar products show that within a 95% confidence interval, the carbon emission results of the product present a log-normal distribution, thus providing enterprises with a reliable carbon emission forecasting and management tool.
[0120] In the above process, quality verification ensures the accuracy of the data, while sensitivity analysis evaluates the impact of input data and assumed variables on the evaluation results, enhancing the reliability of the evaluation results. Taking into account the uncertainty of the data, uncertainty analysis is performed to evaluate the impact of different input parameters on the final results, and the uncertainty of the results is quantified by setting the distribution of input parameters and conducting statistical analysis.
[0121] After processing and verification in the above steps, a verified special steel carbon emission life cycle model can be obtained, which can be used to evaluate and manage carbon emissions in the special steel production process and to carry out environmental management and optimization control.
[0122] The carbon emission prediction device for special steel provided by the present invention is described below. The carbon emission prediction device for special steel described below and the carbon emission prediction method for special steel described above can be referenced to each other.
[0123] like Figure 3 As shown, the carbon emission prediction device for special steel according to an embodiment of the present invention includes a receiving module 310 , an analyzing module 320 , a first processing module 330 , a second processing module 340 , a parameter updating module 350 and a prediction module 360 .
[0124] The receiving module 310 is used to receive target request information input by a user;
[0125] The parsing module 320 is used to parse the target request information and identify the process flow information associated with the life cycle of special steel;
[0126] The first processing module 330 is used to determine the target submodule and the initial input parameters of the target submodule from the special steel carbon emission life cycle model based on the process information; the target submodule includes interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the special steel production process, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transmission and calculation of the target data in the target unit;
[0127] The second processing module 340 is used to determine the associated submodules that have interaction or data transmission with the target submodule based on the process flow information and the target submodule;
[0128] The parameter updating module 350 is used to adjust the initial input parameters based on the initial input parameters and the association relationship between the target submodule and the associated submodule to obtain updated target input parameters;
[0129] The prediction module 360 is used to input the target input parameters into the target submodule to obtain the carbon emission prediction result output by the target submodule.
[0130] The carbon emission prediction device for special steel provided in an embodiment of the present invention receives target request information input by a user, identifies process flow information associated with the life cycle of special steel, and then obtains the initial input parameters of the model, the target sub-module, and the associated sub-module that interacts or transmits data with the target sub-module, thereby realizing modular data output capability, and then the initial input parameters can be adjusted according to the associated relationship to obtain updated target input parameters, and more accurate input parameters for specific links and specific target sub-modules can be determined according to customized needs, thereby obtaining the carbon emission prediction results output by the target sub-module, providing a more flexible and accurate evaluation.
[0131] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor (processor) 410 , a communication interface (Communications Interface) 420 , a memory (memory) 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other through the communication bus 440 . The processor 410 can call the logic instructions in the memory 430 to execute the carbon emission prediction method for special steel, which includes: receiving target request information input by the user; parsing the target request information to identify the process flow information associated with the life cycle of special steel; based on the process flow information, determining the target submodule and the initial input parameters of the target submodule from the carbon emission life cycle model of special steel; the target submodule includes interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the production process of special steel, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transmission and calculation of target data in the target unit; based on the process flow information and the target submodule, determining the associated submodule that interacts with or transmits data to the target submodule; based on the initial input parameters and the association relationship between the target submodule and the associated submodule, adjusting the initial input parameters to obtain updated target input parameters; inputting the target input parameters into the target submodule to obtain the carbon emission prediction result output by the target submodule.
[0132] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0133] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the carbon emission prediction method for special steel provided by the above-mentioned methods, which includes: receiving target request information input by a user; parsing the target request information to identify process flow information associated with the life cycle of special steel; based on the process flow information, determining a target submodule and initial input parameters of the target submodule from a carbon emission life cycle model of special steel; the target submodule includes interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the production process of special steel, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transmission and calculation of target data in the target unit; based on the process flow information and the target submodule, determining an associated submodule that interacts with or transmits data to the target submodule; based on the initial input parameters and the association relationship between the target submodule and the associated submodule, adjusting the initial input parameters to obtain updated target input parameters; inputting the target input parameters into the target submodule to obtain the carbon emission prediction result output by the target submodule.
[0134] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the carbon emission prediction method for special steel provided by the above-mentioned methods, the method comprising: receiving target request information input by a user; parsing the target request information to identify process flow information associated with the life cycle of special steel; based on the process flow information, determining a target submodule and initial input parameters of the target submodule from a carbon emission life cycle model of special steel; the target submodule comprises interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the production process of special steel, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transmission and calculation of target data in the target unit; based on the process flow information and the target submodule, determining an associated submodule that interacts with or transmits data to the target submodule; based on the initial input parameters and the association relationship between the target submodule and the associated submodule, adjusting the initial input parameters to obtain updated target input parameters; inputting the target input parameters into the target submodule to obtain the carbon emission prediction result output by the target submodule.
[0135] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0136] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for predicting carbon emissions of special steel, characterized in that: include: Receive target request information input by the user; Parsing the target request information to identify process flow information associated with the life cycle of special steel; Based on the process information, a target submodule and initial input parameters of the target submodule are determined from the special steel carbon emission life cycle model; the target submodule includes interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the special steel production process, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transmission and calculation of the target data in the target unit; Based on the process flow information and the target submodule, determining an associated submodule that has interaction or data transmission with the target submodule; Based on the initial input parameter and the association relationship between the target submodule and the association submodule, the initial input parameter is adjusted to obtain an updated target input parameter; Inputting the target input parameter into the target submodule to obtain the carbon emission prediction result output by the target submodule; The special steel carbon emission life cycle model is established through the following steps: Collecting input and output data of each process flow, and matching the input and output data with the target data; The carbon dioxide emissions of each target unit under each process are cumulatively calculated according to the functional unit, and matched to the corresponding submodule of each process in the initial special steel carbon emission life cycle model; The initial special steel carbon emission life cycle model was verified through iron balance calculation, mass balance calculation and sensitivity analysis to obtain the final special steel carbon emission life cycle model. The association relationship includes an input-output relationship, and the input-output relationship is used to determine the transmission relationship of data between different sub-modules; The adjusting the initial input parameter based on the initial input parameter and the association relationship between the target submodule and the association submodule to obtain the updated target input parameter includes: Determining the associated parameters of each associated submodule based on the initial input parameters and the associated relationship between the target submodule and the associated submodule; the associated parameters include parameters output by each associated submodule to the target submodule, or parameters output by the target submodule to each associated submodule; When the parameters output by the associating submodule to the target submodule do not meet the requirements of the target submodule, or the parameters output by the target submodule to the associating submodule do not meet the requirements of the associating submodule, adjusting the initial input parameters to obtain updated target input parameters; The step of inputting the target input parameter into the target submodule to obtain the carbon emission prediction result output by the target submodule includes: Using the target input parameters as input data for each target unit; Based on the target logic, determine the allocation ratio of each parameter among the target units and the carbon emission calculation rules of each target unit to obtain the carbon emission prediction results of each target unit; The process links of the process flow information include at least one of sintering, coking, blast furnace, electric furnace, ironmaking, steelmaking, continuous casting, die casting, and rolling; the target data includes at least one of raw material data, auxiliary material data, energy data, product data, by-product data, atmospheric emission data, water emission data, and solid waste data.
2. The carbon emission prediction method for special steel according to claim 1, characterized in that: The association relationship also includes data dependency, time relationship, resource relationship, space relationship, quality relationship and economic relationship; the data dependency relationship is used to indicate the consistency or coordination of data between sub-modules; the time relationship is used to indicate that each sub-module performs calculations and data transmission in a set time sequence; the resource relationship is used to indicate the sharing and competition relationship of resources among sub-modules to achieve the allocation of resources among different sub-modules; the space relationship is used to indicate the layout relationship of sub-modules in physical space; the quality relationship is used to indicate the relationship between the quality of the output of each sub-module and the quality of the input of the sub-module; the economic relationship is used to indicate the cost and benefit relationship of each sub-module.
3. A carbon emission prediction device for special steel, characterized in that: include: A receiving module, used for receiving target request information input by a user; A parsing module, used to parse the target request information and identify process flow information associated with the life cycle of special steel; A first processing module is used to determine a target submodule and initial input parameters of the target submodule from a special steel carbon emission life cycle model based on the process flow information; the target submodule includes interrelated target data, target units and target logic; the target data is used to represent various types of data involved in the special steel production process, the target unit is used to represent various types of equipment and process units used in the production process, and the target logic is used to connect and coordinate the transfer and calculation of the target data in the target unit; A second processing module, configured to determine, based on the process information and the target submodule, an associated submodule that interacts with or transfers data to the target submodule; A parameter updating module, configured to adjust the initial input parameters based on the initial input parameters and the association relationship between the target submodule and the associated submodule to obtain updated target input parameters; the association relationship includes an input-output relationship, and the input-output relationship is used to determine the data transmission relationship between different submodules. The parameter updating module is also configured to determine the association parameters of each associated submodule based on the initial input parameters and the association relationship between the target submodule and the associated submodule; the association parameters include parameters output by each associated submodule to the target submodule, or parameters output by the target submodule to each associated submodule; when the parameters output by the associated submodule to the target submodule do not meet the requirements of the target submodule, or the parameters output by the target submodule to the associated submodule do not meet the requirements of the associated submodule, the initial input parameters are adjusted to obtain updated target input parameters; A prediction module, used to input the target input parameter into the target submodule to obtain the carbon emission prediction result output by the target submodule; the prediction module is also used to use the target input parameter as input data of each target unit; based on the target logic, determine the allocation ratio of each parameter among the target units and the carbon emission calculation rule of each target unit to obtain the carbon emission prediction result of each target unit; The special steel carbon emission life cycle model is established through the following steps: collecting input and output data of each process flow, and matching the input and output data with the target data; accumulating and calculating the carbon dioxide emissions of each target unit under each process flow according to the functional unit, and matching it to the corresponding submodule of each process flow in the initial special steel carbon emission life cycle model; verifying the initial special steel carbon emission life cycle model through iron balance accounting, mass balance accounting and sensitivity analysis to obtain the final special steel carbon emission life cycle model; The process links of the process flow information include at least one of sintering, coking, blast furnace, electric furnace, ironmaking, steelmaking, continuous casting, die casting, and rolling; the target data includes at least one of raw material data, auxiliary material data, energy data, product data, by-product data, atmospheric emission data, water emission data, and solid waste data.
4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, the carbon emission prediction method for special steel as described in claim 1 or 2 is implemented.
5. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the carbon emission prediction method for special steel as claimed in claim 1 or 2 is implemented.
