CN117973637A - A method and system for predicting carbon emissions based on an electricity-carbon correlation model - Google Patents
A method and system for predicting carbon emissions based on an electricity-carbon correlation model Download PDFInfo
- Publication number
- CN117973637A CN117973637A CN202410369795.7A CN202410369795A CN117973637A CN 117973637 A CN117973637 A CN 117973637A CN 202410369795 A CN202410369795 A CN 202410369795A CN 117973637 A CN117973637 A CN 117973637A
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- carbon
- electricity consumption
- model
- correlation model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Water Supply & Treatment (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a carbon emission prediction method and system based on an electric carbon correlation model, and relates to the technical field of carbon emission prediction. The method comprises the following steps: determining carbon emission sources of all links in the steel production flow, and constructing a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission amounts; constructing an electric carbon model of the iron and steel enterprise according to the relation between the carbon emission calculation model and the electricity consumption, wherein the electric carbon model of the iron and steel enterprise is formed by adding a direct carbon emission correlation model and an indirect carbon emission correlation model; and predicting the carbon emission by using an electric carbon model of the iron and steel enterprise. According to the invention, the electric carbon model of the iron and steel enterprise is built by building the correlation model of the electricity consumption and the direct carbon emission and the correlation model of the electricity consumption and the indirect carbon emission, so that the problems of imperfect data set construction and poor model prediction accuracy caused by incapacitation of partial data without considering the correlation between data in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of carbon emission prediction, in particular to a carbon emission prediction method and system based on an electric carbon correlation model.
Background
The steel industry is a typical high energy consumption and high carbon emission industry. In order to meet the development trend of the existing green economy, carbon emission prediction and modeling technology has become a research topic of great concern. Currently, there are few studies associated with industrial carbon emission prediction. The establishment of the electric carbon model in the steel industry not only can promote the industrial development, but also has great economic and environmental significance.
The data relating to carbon emissions in the steel industry includes electricity consumption, fossil energy consumption, raw material consumption, steel production, and carbon emissions from various other carbon emissions sources. Factors affecting carbon emissions include the model of the production facility, the type of fossil energy source, and the production yield. At present, the research on carbon emission prediction is mainly focused on multiple influencing factors, prediction objects are mainly buildings, provinces and urban areas and the like, the research on carbon emission prediction of industrial enterprises, particularly steel industry is less, and the current common prediction method comprises a gray model, a BP neural network and other methods, and the establishment of the prediction model is mainly based on the influencing factors and historical trends. Because most of the existing carbon emission prediction methods are concentrated on multi-factor prediction, the problems of difficult data acquisition, insufficient overall mining of associated information among various data and the like exist, and various data cannot be effectively quantized for carbon emission prediction, so that the final prediction accuracy is affected.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a carbon emission prediction method and a system based on an electric carbon correlation model, which are used for accurately predicting the carbon emission of a steel enterprise by analyzing the carbon emission of each link in the steel production process, selecting the steel yield as a correlation variable, establishing a correlation model of electricity consumption and direct carbon emission and further combining the correlation model of electricity consumption and indirect carbon emission to construct an electric carbon model of the steel industry.
In order to achieve the above object, the present invention is realized by the following technical scheme:
the first aspect of the invention provides a carbon emission prediction method based on an electric carbon correlation model, which comprises the following steps:
Determining carbon emission sources of all links in the steel production flow according to the whole process carbon emission track of the steel enterprise, and constructing a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission amounts;
Constructing an electric carbon model of the iron and steel enterprise according to the relation between the carbon emission calculation model and the electricity consumption, wherein the electric carbon model of the iron and steel enterprise is formed by adding a direct carbon emission correlation model and an indirect carbon emission correlation model, the indirect carbon emission correlation model is constructed according to the relation between the electricity consumption and the indirect carbon emission, and the direct carbon emission correlation model is constructed according to the relation among the electricity consumption, related variables and the direct carbon emission relation;
And predicting the carbon emission by using an electric carbon model of the iron and steel enterprise.
Further, carbon emissions sources include carbon emissions generated by electricity used by production facilities, carbon emissions generated by industrial processes, and carbon emissions generated by combustion of fossil fuels.
Further, steel yield is selected as a related variable.
Further, the construction process of the direct carbon emission correlation model comprises the following steps:
Acquiring the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data;
calculating the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission;
and calculating the relation between the electricity consumption and the carbon emission according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, and obtaining a direct carbon emission correlation model.
Further, the specific steps of obtaining the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data are as follows:
obtaining historical annual data of the electricity consumption of each enterprise in the steel industry, the indirect carbon emission of the electricity consumption and the carbon emission of steel production through the electricity consumption of each enterprise in the steel industry and the carbon emission of each emission source in a steel industry carbon emission accounting report;
Preprocessing historical annual data, wherein the proportion range of the integrated electricity consumption of unit steel production and the integrated carbon emission of unit steel production of China steel enterprises is selected as a data preprocessing standard, and data which are not in the proportion range are discarded;
and (3) calculating the comprehensive electricity consumption of the unit steel yield and the comprehensive carbon emission of the unit steel production of the preprocessed data.
Further, a correlation model of the product yield and the electricity consumption is obtained according to the relation between the related variable and the electricity consumption, a correlation model of the product yield and the carbon emission is obtained according to the relation between the related variable and the carbon emission, the relation between the electricity consumption and the carbon emission is calculated, and the correlation model of the product yield and the electricity consumption and the correlation model of the product yield and the carbon emission are divided to obtain a correlation model of the electricity consumption and the direct carbon emission, so that the direct carbon emission correlation model is obtained.
Further, a support vector machine prediction model is built according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission by adopting a support vector machine curve fitting mode, the support vector machine prediction model is trained by adopting historical data, and the relation expression between the electricity consumption and the carbon emission is optimized to obtain optimal support vector machine prediction model parameters, so that a direct carbon emission correlation model is formed.
The second aspect of the present invention provides a carbon emission prediction system based on an electric carbon correlation model, comprising:
The carbon emission source determining module is configured to determine carbon emission sources of all links in the steel production flow according to the whole process carbon emission track of the steel enterprise, and construct a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission amounts;
The system comprises an electric carbon model construction module, a direct carbon emission correlation model and an indirect carbon emission correlation model, wherein the electric carbon model construction module is configured to construct an electric carbon model of an iron and steel enterprise according to the relation between a carbon emission calculation model and electricity consumption, the electric carbon model of the iron and steel enterprise is formed by adding the direct carbon emission correlation model and the indirect carbon emission correlation model, the indirect carbon emission correlation model is constructed according to the relation between the electricity consumption and the indirect carbon emission, and the direct carbon emission correlation model is constructed according to the relation among the electricity consumption, related variables and the direct carbon emission relation;
And the carbon emission prediction module is configured to predict the carbon emission by using an electric carbon model of the iron and steel enterprise.
Further, carbon emissions sources include carbon emissions generated by electricity used by production facilities, carbon emissions generated by industrial processes, and carbon emissions generated by combustion of fossil fuels.
Further, steel yield is selected as a related variable.
Further, the electrical carbon model construction module includes a direct carbon emission correlation model training module for construction and training of a direct carbon emission correlation model configured to:
Acquiring the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data;
calculating the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission;
and calculating the relation between the electricity consumption and the carbon emission according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, and obtaining a direct carbon emission correlation model.
Furthermore, the direct carbon emission correlation model training module further comprises a data preprocessing module, which is used for acquiring the comprehensive electricity consumption of the unit correlation variable and the comprehensive carbon emission of the unit correlation variable in the historical data:
obtaining historical annual data of the electricity consumption of each enterprise in the steel industry, the indirect carbon emission of the electricity consumption and the carbon emission of steel production through the electricity consumption of each enterprise in the steel industry and the carbon emission of each emission source in a steel industry carbon emission accounting report;
Preprocessing historical annual data, wherein the proportion range of the integrated electricity consumption of unit steel production and the integrated carbon emission of unit steel production of China steel enterprises is selected as a data preprocessing standard, and data which are not in the proportion range are discarded;
and (3) calculating the comprehensive electricity consumption of the unit steel yield and the comprehensive carbon emission of the unit steel production of the preprocessed data.
Further, the direct carbon emission correlation model training module is further configured to obtain a correlation model of product yield and electricity consumption according to the relation between the related variable and electricity consumption, obtain a correlation model of product yield and carbon emission according to the relation between the related variable and carbon emission, calculate the relation between the electricity consumption and carbon emission, and divide the two models of the correlation model of product yield and electricity consumption and the correlation model of product yield and carbon emission to obtain a correlation model of electricity consumption and direct carbon emission to obtain a direct carbon emission correlation model.
Still further, the direct carbon emission correlation model training module is further configured to: and constructing a support vector machine prediction model according to the relation between the related variable and the power consumption and the relation between the related variable and the carbon emission by adopting a curve fitting mode of the support vector machine, training the support vector machine prediction model by adopting historical data, optimizing the relation expression between the power consumption and the carbon emission, obtaining optimal support vector machine prediction model parameters, and forming a direct carbon emission association model.
The one or more of the above technical solutions have the following beneficial effects:
The invention discloses a carbon emission prediction method and a system based on an electric carbon correlation model, which fully consider the relation between direct carbon emission and indirect carbon emission and electricity consumption when predicting the carbon emission of a steel enterprise, and respectively establish the correlation models of the direct carbon emission and the electricity consumption and the indirect carbon emission and the electricity consumption based on the historical data of the steel enterprise, thereby combining and forming the electric carbon model of the steel enterprise and realizing the accurate prediction of the carbon emission of the steel enterprise.
When the electric carbon model of the iron and steel enterprise is built, the SVR prediction model is built by adopting a SVR curve fitting method, so that the basic form of the electric carbon model of the iron and steel enterprise is obtained, and the finally predicted carbon emission is more accurate.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flowchart of a method for predicting carbon emissions based on an electrical carbon correlation model in accordance with a first embodiment of the present invention;
FIG. 2 is a schematic view of carbon emissions during steel production;
FIG. 3 is a schematic diagram of a modeling process of an electric carbon model of an iron and steel enterprise in accordance with the first embodiment of the present invention;
FIG. 4 is a schematic diagram of a SVR prediction model construction process according to a first embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, 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 belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof;
embodiment one:
The first embodiment of the invention provides a carbon emission prediction method based on an electric carbon correlation model, as shown in fig. 1, the technical method of carbon emission of an iron and steel enterprise is provided according to the mapping relation between the iron and steel production process and the carbon emission, and an electric carbon model of the iron and steel enterprise is further established, wherein the electric carbon model of the iron and steel enterprise comprises a correlation model of electricity consumption and direct carbon emission and a correlation model of electricity consumption and indirect carbon emission. And (3) through acquiring historical data of the iron and steel enterprises, establishing an SVR prediction model by adopting a support vector machine curve fitting method, and predicting the carbon emission.
The method specifically comprises the following steps:
S1: determining carbon emission sources of all links in the steel production flow according to the whole process carbon emission track of the steel enterprise, and constructing a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission.
As shown in fig. 2, the steel production process can be mainly summarized as the following steps:
Step 1, sintering of iron ore, pelletizing and coking of coal. This step produces carbon emissions, primarily through combustion reactions, the source of which is fossil fuel combustion.
And 2, conveying the product obtained in the step 1 into a blast furnace for iron making. Specifically comprises the pretreatment of molten iron, and the pretreated molten iron is sent into a converter and an electric furnace to be subjected to secondary metallurgy uniformly. This step mainly produces carbon emissions by reduction and combustion reactions, the source of which is the fossil fuel combustion, industrial process.
And 3, placing the product in the step 2 into a continuous casting machine to make steel, wherein carbon emission is mainly generated through electric power and thermal consumption, so that the carbon emission source is electric power consumption.
And 4, feeding the steel refined in the step 3 into a rolling mill for rolling to obtain the required steel. This step produces carbon emissions mainly through electricity and heat consumption, and thus the carbon emission source is electricity consumption.
In summary, the carbon emissions sources include the electricity generated by the production facility, the carbon emissions generated by the industrial process, and the carbon emissions generated by the combustion of fossil fuels.
And constructing a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission amounts. The total carbon emission amount calculation formula is formula (1).
(1)。
In the method, in the process of the invention,Representing the total carbon emission of iron and steel enterprises,/>Represents the amount of CO 2 emitted by the combustion of the fuel, as shown in (2).
(2)。
In the method, in the process of the invention,Represents the activity level of the ith fossil fuel,/>The fuel represents the CO 2 emission factor of the ith fossil fuel and n represents the total number of fossil fuels.
The emission amount of CO 2 generated in the industrial production process is shown as formula (3).
(3)。
CO 2 emissions from flux consumptionIs formula (4).
(4)。
In the method, in the process of the invention,The consumption of the jth flux is expressed in tons (t); /(I)For the CO 2 emission factor of the jth flux, the unit is tco 2/t, k represents the total flux, and the present example calculates the default value for release using the province where the iron and steel plant is located.
In the production process of common steel, the flux mainly considers the consumption of limestone, dolomite and the minimum materials contained in the limestone, wherein the dolomite comprises the consumption of dolomite powder and dolomite blocks, and the limestone comprises the consumption of limestone and limestone blocks produced by a lime kiln. When the method is applied to different steel plants, the flux types are adjusted according to the production conditions of the steel plants to participate in calculation.
CO 2 emissions from electrode consumptionIs equation (5).
(5)。
In the method, in the process of the invention,The mass of the electrode consumed by the electric furnace steelmaking, refining furnace and the like is expressed as ton (t); /(I)The CO 2 emission factor of the consumed electrode of the electric furnace steelmaking, refining furnace and the like is expressed as t CO 2/t.
CO 2 emission amount generated by consumption of carbon-containing raw materials such as pig iron, scrap steel and ferroalloyIs formula (6).
(6)。
In the method, in the process of the invention,The purchase amount of the first carbon-containing raw material is ton (t); /(I)CO 2 emissions factor for the first purchased carbonaceous feedstock, in units of tCO 2/t, m representing the total number of carbonaceous feedstock purchased.
The formula of the carbon emission amount corresponding to the net electricity purchasing is shown as (7).
(7)。
In the method, in the process of the invention,The net electricity purchasing quantity is obtained by using electricity consumption of production equipment in the production process. /(I)CO 2 emission coefficient for power supply.
S2: and constructing an electric carbon model of the iron and steel enterprise according to the relation between the carbon emission calculation model and the electricity consumption, wherein the electric carbon model of the iron and steel enterprise is formed by adding a direct carbon emission correlation model and an indirect carbon emission correlation model, the indirect carbon emission correlation model is constructed according to the relation between the electricity consumption and the indirect carbon emission, and the direct carbon emission correlation model is constructed according to the relation among the electricity consumption, the related variables and the direct carbon emission relation. In this example, steel yield was chosen as the relevant variable.
In one embodiment, the amount of electricity used is linear with the carbon emissions generated by the amount of electricity used, as shown in equation (7). The present embodiment classifies carbon emissions in the steel industry into direct carbon emissions and indirect carbon emissions. Since there is no direct relation between the electricity consumption and the direct carbon emission, the correlation between the two is established by selecting the relevant variable, namely the production of steel in this embodiment. The construction process of the electricity consumption and carbon emission correlation model is as shown in fig. 3, the historical data of an enterprise are input to obtain the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable, the data are preprocessed, whether the data are used for direct calculation of electric carbon conversion is judged, if yes, the electricity consumption and indirect carbon emission correlation model is established, and if no, the electricity consumption and the related variable are modeled, and the electricity consumption and direct carbon emission correlation model is obtained. And finally, adding the two correlation models to obtain a total correlation model of the electricity consumption and the carbon emission, namely an electric carbon model of the iron and steel enterprise.
The direct carbon emission correlation model establishment process comprises the following steps: obtaining a correlation model of the product yield and the electricity consumption according to the relation between the related variable and the electricity consumption, obtaining a correlation model of the product yield and the carbon emission according to the relation between the related variable and the carbon emission, calculating the relation between the electricity consumption and the carbon emission, and dividing the two models of the correlation model of the product yield and the electricity consumption and the correlation model of the product yield and the carbon emission to obtain a correlation model of the electricity consumption and the direct carbon emission to obtain a direct carbon emission correlation model.
The specific steps are as follows:
(1) And acquiring the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data.
According to the embodiment, historical annual data of the electricity consumption of each enterprise in the steel industry, the indirect carbon emission of the electricity consumption and the carbon emission of steel production are obtained through the electricity consumption of each enterprise in the steel industry and the carbon emission of each emission source in a carbon emission accounting report in the steel industry. Based on the historical data of the iron and steel enterprises, the embodiment adopts a curve fitting method to find out the parameters of the basic form of the electricity consumption-carbon emission model of the industry. The required data include the company's electricity consumption, steel production, indirect carbon emissions from electricity consumption, and direct carbon emissions from electricity production.
First, data is preprocessed. And referring to main product energy efficiency indexes of the steel industry in national industrial energy efficiency guidelines, selecting a ratio range of the integrated electricity consumption of unit steel output and the integrated carbon emission of unit steel production of China steel enterprises as a data preprocessing standard, and discarding data which are not in the ratio range.
The proportion range is determined according to the proportion of most enterprises in the industry, and the comprehensive electricity consumption of the enterprise unit steel output is considered to be lower than the range, namely, the electricity supplied by the self-contained power plant of the enterprise is not counted into the statistical process. If the comprehensive electricity consumption per unit steel yield is higher than the range, the carbon emission reduction technology of enterprises is considered to be improved.
The comprehensive electricity consumption per unit steel production and the comprehensive carbon emission per unit steel production are calculated as (8) and (9), respectively.
(8)。
(9)。
In the method, in the process of the invention,Is the comprehensive electricity consumption of unit steel yield;/>Is the electricity consumption, and has the unit of MWh/(Is the yield of steel in ton; -Is the comprehensive carbon emission of steel production units;/>Is the standard coal consumption, the unit is kg; -Is the standard coal carbon emission coefficient with the unit of tc/tce; -The carbon emission is given in tc.
(2) And calculating the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission.
At present, the carbon emission of steel is calculated by adopting a carbon emission coefficient method, so that an accurate result can be obtained. However, the method has the problems of difficult data acquisition, complex calculation method and the like. Therefore, the present embodiment selects readily available electricity consumption as an input for predicting carbon emissions. However, in the production process of the steel industry, carbon emissions generated by fossil fuel combustion and industrial production processes are included in addition to the electricity consumption, which results in a problem that the prediction result of directly modeling the electricity consumption to carbon emissions is not ideal.
As can be seen from fig. 2, the carbon emission sources of the iron and steel enterprises include carbon emissions generated by electricity of production facilities, carbon emissions generated by industrial processes, and carbon emissions generated by combustion of fossil fuels. The carbon emission sources, i.e., indirect carbon emission, of steel other than electricity consumption are related to raw material consumption, and are represented by the formulas (10) and (11).
(10)。
(11)。
In the method, in the process of the invention,Represents the CO 2 emission amount generated by fuel combustion; /(I)Representing activity levels of fossil fuels; /(I)Representing the consumption of raw materials for steel production; /(I)Expressed as/>Is an independent variable,/>As a function of the dependent variable; /(I)Expressed in terms ofIs an independent variable,/>As a function of the dependent variable; /(I)Expressed as/>As a function of the argument; /(I)Expressed as/>As a function of the argument; /(I)Expressed as/>As a function of the argument; /(I)Expressed as/>Is an independent variable,/>As a function of the dependent variable; /(I)Expressed as/>Is an independent variable,/>As a function of the dependent variable; /(I)Expressed as/>Is an independent variable,/>As a function of the dependent variable.
According to the equation. From (10) and (11), it is known that the direct carbon emissions generated by iron and steel enterprises are related to the consumption of raw materials. However, the consumption of raw materials is difficult to monitor, but there is a high correlation between the consumption of raw materials and the yield of products. Therefore, the expression (10) and the expression (11) are converted into functional expressions having the steel yield as an independent variable, that is, the expression (12) and the expression (13).
(12)。
(13)。
In the method, in the process of the invention,Is the yield of steel; /(I)Expressed as/>Is an independent variable,/>As a function of the dependent variable; /(I)Expressed as/>Is an independent variable,/>As a function of the dependent variable. From the above analysis, it can be seen that the direct carbon emissions are related to the product yield. Because the electricity consumption and the product yield have strong correlation, the steel yield can be selected as a related variable, and a relation model of the electricity consumption and the direct carbon emission is established.
(3) And calculating the relation between the electricity consumption and the carbon emission according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, namely constructing two models of a correlation model of the product yield and the electricity consumption and a correlation model of the product yield and the carbon emission in a curve fitting mode, and finally dividing the two models to obtain a direct carbon emission correlation model.
In this embodiment, a support vector machine curve fitting mode is adopted to construct a support vector machine prediction model according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, historical data is adopted to train the support vector machine prediction model, and the relation expression between the electricity consumption and the carbon emission is optimized to obtain optimal support vector machine prediction model parameters, so as to form a correlation model of the electricity consumption and the direct carbon emission, namely a direct carbon emission correlation model.
Support vector regression (Support Vector Regression, SVR) is a method of fitting a curve using a support vector machine (Support Vector Machines, SVM). The method is commonly used for regression analysis and has the characteristics of small sample, nonlinearity, high-dimensional pattern recognition and the like. The efficiency and performance of SVR is affected by the kernel function type, kernel parameter Y, and penalty parameter C, which are typically empirically determined, but this increases errors and decreases operating speed. The influence of human factors can be avoided through parameter searching. The implementation steps are as shown in fig. 4, preprocessing the acquired N groups of enterprise month data, classifying the enterprise month data into N groups, taking m groups of data as training data, performing model training through optimization of parameters C and Y, and performing model test on the trained model by N-m groups of test data to obtain a test result.
In this embodiment, the training process for the direct carbon emission correlation model is:
(1) N groups of monthly electricity consumption data, steel output data and carbon emission data of a certain steel enterprise are obtained, data preprocessing is carried out, singular data are removed, and a sample set containing the N groups of data is formed.
(2) M samples from the sample set are selected to form a training sample set, and the remaining n-m samples form a test sample set. And selecting a kernel function to process the training sample set and establishing an SVR model. And optimizing the values of the penalty parameter C and the kernel function parameter Y by adopting a lattice search and cross-validation method. And finally, obtaining optimal parameters and establishing an SVR prediction model.
(3) And simulating the data of the training sample set to obtain an optimal solution of the model and the regression function f (x). And substituting all data of the training sample set and the test sample set into the function to output fitting values, and comparing the fitting results with actual data. And carrying out linear regression on the value, and judging the learning and lifting capacity of the model according to the result of the correlation coefficient R2. If the model learning and popularization capabilities are poor, the parameter optimization step is required to be returned until the optimal solution is obtained, and the relation between the electricity consumption and the carbon emission can be obtained.
S3: and predicting the carbon emission by using an electric carbon model of the iron and steel enterprise.
When the carbon emission amount of the iron and steel enterprises is predicted, the relation between the direct carbon emission and the indirect carbon emission and the electricity consumption is fully considered, the electricity consumption and the indirect carbon emission are used when the electricity is converted according to the direct calculation, the principles of the electricity consumption, the steel yield and the direct carbon emission are used when the electricity is converted, the correlation models of the direct carbon emission and the electricity consumption and the indirect carbon emission and the electricity consumption are respectively established, the basic form of the electric carbon model of the iron and steel enterprises is obtained, and the accurate prediction of the carbon emission of the iron and steel enterprises is realized. In the embodiment, the carbon emission of each link in the steel production process is analyzed, the steel yield is selected as a related variable, a SVR prediction model is established by adopting a SVR curve fitting method based on historical data of a steel enterprise, and a basic form of an electric carbon model in the steel industry is obtained.
Embodiment two:
The second embodiment of the invention provides a carbon emission prediction system based on an electric carbon correlation model, which comprises:
the carbon emission source determining module is configured to determine carbon emission sources of all links in the steel production flow according to the whole process carbon emission track of the steel enterprise, and construct a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission amounts.
Among the carbon emissions sources include carbon emissions generated by the electricity used by the production facility, carbon emissions generated by the industrial process, and carbon emissions generated by the combustion of fossil fuels.
The electric carbon model construction module is configured to construct an electric carbon model of the iron and steel enterprise according to the relation between the carbon emission calculation model and the electricity consumption, wherein the electric carbon model of the iron and steel enterprise is formed by adding a direct carbon emission correlation model and an indirect carbon emission correlation model, the direct carbon emission correlation model is constructed according to the relation between the electricity consumption and the direct carbon emission, and the indirect carbon emission correlation model is constructed according to the relation among the electricity consumption, the related variables and the indirect carbon emission relation. In this example, steel yield was chosen as the relevant variable.
The electrical carbon model construction module includes a direct carbon emission correlation model training module for construction and training of a direct carbon emission correlation model configured to:
Acquiring the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data;
calculating the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission;
and calculating the relation between the electricity consumption and the carbon emission according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, and obtaining a direct carbon emission correlation model.
The direct carbon emission correlation model training module further comprises a data preprocessing module, wherein the data preprocessing module is used for acquiring the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data:
obtaining historical annual data of the electricity consumption of each enterprise in the steel industry, the indirect carbon emission of the electricity consumption and the carbon emission of steel production through the electricity consumption of each enterprise in the steel industry and the carbon emission of each emission source in a steel industry carbon emission accounting report;
Preprocessing historical annual data, wherein the proportion range of the integrated electricity consumption of unit steel production and the integrated carbon emission of unit steel production of China steel enterprises is selected as a data preprocessing standard, and data which are not in the proportion range are discarded;
and (3) calculating the comprehensive electricity consumption of the unit steel yield and the comprehensive carbon emission of the unit steel production of the preprocessed data.
The direct carbon emission correlation model training module is further configured to obtain a correlation model of the product yield and the electricity consumption according to the relation between the related variable and the electricity consumption, obtain a correlation model of the product yield and the carbon emission according to the relation between the related variable and the carbon emission, calculate the relation between the electricity consumption and the carbon emission, and divide the two models of the correlation model of the product yield and the electricity consumption and the correlation model of the product yield and the carbon emission to obtain a correlation model of the electricity consumption and the direct carbon emission, so as to obtain the direct carbon emission correlation model.
The direct carbon emission correlation model training module is further configured to: and constructing a support vector machine prediction model according to the relation between the related variable and the power consumption and the relation between the related variable and the carbon emission by adopting a curve fitting mode of the support vector machine, training the support vector machine prediction model by adopting historical data, optimizing the relation expression between the power consumption and the carbon emission, obtaining optimal support vector machine prediction model parameters, and forming a direct carbon emission association model.
And the carbon emission prediction module is configured to predict the carbon emission by using an electric carbon model of the iron and steel enterprise.
The steps involved in the second embodiment correspond to those of the first embodiment of the method, and the detailed description of the second embodiment can be found in the related description section of the first embodiment.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (14)
1. The carbon emission prediction method based on the electric carbon correlation model is characterized by comprising the following steps of:
Determining carbon emission sources of all links in the steel production flow according to the whole process carbon emission track of the steel enterprise, and constructing a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission amounts;
Constructing an electric carbon model of the iron and steel enterprise according to the relation between the carbon emission calculation model and the electricity consumption, wherein the electric carbon model of the iron and steel enterprise is formed by adding a direct carbon emission correlation model and an indirect carbon emission correlation model, the indirect carbon emission correlation model is constructed according to the relation between the electricity consumption and the indirect carbon emission, and the direct carbon emission correlation model is constructed according to the relation among the electricity consumption, related variables and the direct carbon emission relation;
And predicting the carbon emission by using an electric carbon model of the iron and steel enterprise.
2. The method for predicting carbon emissions based on an electrical carbon correlation model of claim 1, wherein the carbon emissions sources comprise production facility electricity generated carbon emissions, industrial process generated carbon emissions, and fossil fuel combustion generated carbon emissions.
3. The method for predicting carbon emissions based on an electrical carbon correlation model of claim 1, wherein steel yield is selected as the correlation variable.
4. The method for predicting carbon emissions based on an electrical carbon correlation model as claimed in claim 1, wherein the process of constructing the direct carbon emission correlation model comprises:
Acquiring the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data;
calculating the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission;
and calculating the relation between the electricity consumption and the carbon emission according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, and obtaining a direct carbon emission correlation model.
5. The method for predicting carbon emissions based on an electric carbon correlation model as claimed in claim 4, wherein the specific steps of obtaining the integrated electricity consumption of the unit related variable and the integrated carbon emissions of the unit related variable in the history data are:
obtaining historical annual data of the electricity consumption of each enterprise in the steel industry, the indirect carbon emission of the electricity consumption and the carbon emission of steel production through the electricity consumption of each enterprise in the steel industry and the carbon emission of each emission source in a steel industry carbon emission accounting report;
Preprocessing historical annual data, wherein the proportion range of the integrated electricity consumption of unit steel production and the integrated carbon emission of unit steel production of China steel enterprises is selected as a data preprocessing standard, and data which are not in the proportion range are discarded;
and (3) calculating the comprehensive electricity consumption of the unit steel yield and the comprehensive carbon emission of the unit steel production of the preprocessed data.
6. The method for predicting carbon emissions based on an electric carbon correlation model of claim 4, wherein the correlation model of product yield and electricity consumption is obtained from a relation between a related variable and electricity consumption, the correlation model of product yield and carbon emissions is obtained from a relation between a related variable and carbon emissions, the relation between electricity consumption and carbon emissions is calculated, and the correlation model of electricity consumption and direct carbon emissions is obtained by dividing the two models of the correlation model of product yield and electricity consumption and the correlation model of product yield and carbon emissions.
7. The method for predicting carbon emission based on an electric carbon correlation model as claimed in claim 4, wherein a support vector machine curve fitting mode is adopted to construct a support vector machine prediction model according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, historical data is adopted to train the support vector machine prediction model, and the relation expression between the electricity consumption and the carbon emission is optimized to obtain optimal support vector machine prediction model parameters, so as to form a direct carbon emission correlation model.
8. A carbon emission prediction system based on an electric carbon correlation model, comprising:
The carbon emission source determining module is configured to determine carbon emission sources of all links in the steel production flow according to the whole process carbon emission track of the steel enterprise, and construct a carbon emission calculation model according to the mapping relation between different carbon emission sources and carbon emission amounts;
The system comprises an electric carbon model construction module, a direct carbon emission correlation model and an indirect carbon emission correlation model, wherein the electric carbon model construction module is configured to construct an electric carbon model of an iron and steel enterprise according to the relation between a carbon emission calculation model and electricity consumption, the electric carbon model of the iron and steel enterprise is formed by adding the direct carbon emission correlation model and the indirect carbon emission correlation model, the indirect carbon emission correlation model is constructed according to the relation between the electricity consumption and the indirect carbon emission, and the direct carbon emission correlation model is constructed according to the relation among the electricity consumption, related variables and the direct carbon emission relation;
And the carbon emission prediction module is configured to predict the carbon emission by using an electric carbon model of the iron and steel enterprise.
9. The electrical carbon correlation model based carbon emission prediction system of claim 8, wherein the carbon emission source comprises production equipment electricity generated carbon emissions, industrial process generated carbon emissions, and fossil fuel combustion generated carbon emissions.
10. The carbon emission prediction system based on the electric carbon correlation model as claimed in claim 8, wherein the steel yield is selected as the correlation variable.
11. The electric carbon correlation model-based carbon emission prediction system of claim 8, wherein the electric carbon model construction module includes a direct carbon emission correlation model training module for construction and training of the direct carbon emission correlation model configured to:
Acquiring the comprehensive electricity consumption of the unit related variable and the comprehensive carbon emission of the unit related variable in the historical data;
calculating the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission;
and calculating the relation between the electricity consumption and the carbon emission according to the relation between the related variable and the electricity consumption and the relation between the related variable and the carbon emission, and obtaining a direct carbon emission correlation model.
12. The electrical carbon-correlation model-based carbon emission prediction system of claim 11, wherein the direct carbon-correlation model training module further comprises a data preprocessing module for obtaining a comprehensive power consumption of the unit-related variables and a comprehensive carbon emission of the unit-related variables in the historical data:
obtaining historical annual data of the electricity consumption of each enterprise in the steel industry, the indirect carbon emission of the electricity consumption and the carbon emission of steel production through the electricity consumption of each enterprise in the steel industry and the carbon emission of each emission source in a steel industry carbon emission accounting report;
Preprocessing historical annual data, wherein the proportion range of the integrated electricity consumption of unit steel production and the integrated carbon emission of unit steel production of China steel enterprises is selected as a data preprocessing standard, and data which are not in the proportion range are discarded;
and (3) calculating the comprehensive electricity consumption of the unit steel yield and the comprehensive carbon emission of the unit steel production of the preprocessed data.
13. The electrical carbon correlation model-based carbon emission prediction system of claim 11, wherein the direct carbon emission correlation model training module is further configured to obtain a correlation model of product yield and electricity consumption based on a relationship between the related variable and electricity consumption, obtain a correlation model of product yield and carbon emission based on a relationship between the related variable and carbon emission, calculate a relationship between electricity consumption and carbon emission, and divide the two models of the correlation model of product yield and electricity consumption and the correlation model of product yield and carbon emission to obtain a correlation model of electricity consumption and direct carbon emission, to obtain a direct carbon emission correlation model.
14. The electrical carbon-correlation model-based carbon emission prediction system of claim 11, wherein the direct carbon-correlation model training module is further configured to: and constructing a support vector machine prediction model according to the relation between the related variable and the power consumption and the relation between the related variable and the carbon emission by adopting a curve fitting mode of the support vector machine, training the support vector machine prediction model by adopting historical data, optimizing the relation expression between the power consumption and the carbon emission, obtaining optimal support vector machine prediction model parameters, and forming a direct carbon emission association model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410369795.7A CN117973637A (en) | 2024-03-29 | 2024-03-29 | A method and system for predicting carbon emissions based on an electricity-carbon correlation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410369795.7A CN117973637A (en) | 2024-03-29 | 2024-03-29 | A method and system for predicting carbon emissions based on an electricity-carbon correlation model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117973637A true CN117973637A (en) | 2024-05-03 |
Family
ID=90846364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410369795.7A Pending CN117973637A (en) | 2024-03-29 | 2024-03-29 | A method and system for predicting carbon emissions based on an electricity-carbon correlation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117973637A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100107171A1 (en) * | 2008-10-24 | 2010-04-29 | International Business Machines Corporation | Computing task carbon offseting |
| US9559521B1 (en) * | 2015-12-09 | 2017-01-31 | King Electric Vehicles Inc. | Renewable energy system with integrated home power |
| US20200372588A1 (en) * | 2019-05-20 | 2020-11-26 | Singularity Energy, Inc. | Methods and systems for machine-learning for prediction of grid carbon emissions |
| CN114399110A (en) * | 2022-01-14 | 2022-04-26 | 国网福建省电力有限公司营销服务中心 | Ceramic industry carbon emission prediction method based on electric power data |
| CN114399111A (en) * | 2022-01-14 | 2022-04-26 | 国网福建省电力有限公司营销服务中心 | Method for predicting carbon emission in flat glass industry based on electrical-carbon correlation |
| CN115409331A (en) * | 2022-08-12 | 2022-11-29 | 天津市普迅电力信息技术有限公司 | Carbon footprint calculation method based on cable type materials |
| CN116823295A (en) * | 2023-08-31 | 2023-09-29 | 国网山东省电力公司营销服务中心(计量中心) | A method, system, equipment and medium for measuring carbon emissions in the steel industry |
| CN117217419A (en) * | 2023-11-07 | 2023-12-12 | 中电山河数字科技(南通)有限公司 | Method and system for monitoring full life cycle carbon emission of industrial production |
| CN117237160A (en) * | 2023-08-24 | 2023-12-15 | 中铁二院工程集团有限责任公司 | Enterprise carbon emission accounting method and system |
-
2024
- 2024-03-29 CN CN202410369795.7A patent/CN117973637A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100107171A1 (en) * | 2008-10-24 | 2010-04-29 | International Business Machines Corporation | Computing task carbon offseting |
| US9559521B1 (en) * | 2015-12-09 | 2017-01-31 | King Electric Vehicles Inc. | Renewable energy system with integrated home power |
| US20200372588A1 (en) * | 2019-05-20 | 2020-11-26 | Singularity Energy, Inc. | Methods and systems for machine-learning for prediction of grid carbon emissions |
| CN114399110A (en) * | 2022-01-14 | 2022-04-26 | 国网福建省电力有限公司营销服务中心 | Ceramic industry carbon emission prediction method based on electric power data |
| CN114399111A (en) * | 2022-01-14 | 2022-04-26 | 国网福建省电力有限公司营销服务中心 | Method for predicting carbon emission in flat glass industry based on electrical-carbon correlation |
| CN115409331A (en) * | 2022-08-12 | 2022-11-29 | 天津市普迅电力信息技术有限公司 | Carbon footprint calculation method based on cable type materials |
| CN117237160A (en) * | 2023-08-24 | 2023-12-15 | 中铁二院工程集团有限责任公司 | Enterprise carbon emission accounting method and system |
| CN116823295A (en) * | 2023-08-31 | 2023-09-29 | 国网山东省电力公司营销服务中心(计量中心) | A method, system, equipment and medium for measuring carbon emissions in the steel industry |
| CN117217419A (en) * | 2023-11-07 | 2023-12-12 | 中电山河数字科技(南通)有限公司 | Method and system for monitoring full life cycle carbon emission of industrial production |
Non-Patent Citations (2)
| Title |
|---|
| 刘宏强;付建勋;刘思雨;谢欣悦;杨笑楹;: "钢铁生产过程二氧化碳排放计算方法与实践", 钢铁, no. 04, 15 April 2016 (2016-04-15) * |
| 黑洞拿铁: "（三）碳排放如何计算_碳排放计算", Retrieved from the Internet <URL:https://blog.csdn.net/m0_60862600/article/details/123254761> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116822714A (en) | Steel product carbon footprint management method and system based on life cycle evaluation | |
| Zhang et al. | Comparison of the Prediction of BOF End‐Point Phosphorus Content Among Machine Learning Models and Metallurgical Mechanism Model | |
| Matino et al. | Quantification of energy and environmental impacts in uncommon electric steelmaking scenarios to improve process sustainability | |
| Shi et al. | Process metallurgy and data-driven prediction and feedback of blast furnace heat indicators | |
| CN120410141B (en) | An intelligent monitoring system and method for fly ash production line based on multi-source data | |
| CN118070645A (en) | Electric furnace end temperature prediction method based on BiLSTM-CNN | |
| Matino et al. | Application of echo state neural networks to forecast blast furnace gas production: pave the way to off-gas optimized management | |
| Niu et al. | Prediction of sinter chemical composition based on ensemble learning algorithms | |
| Yu et al. | Industrial risks assessment for the large-scale development of electric arc furnace steelmaking technology | |
| CN117973637A (en) | A method and system for predicting carbon emissions based on an electricity-carbon correlation model | |
| Runkana et al. | Digital twins for optimization of ironmaking operations | |
| Spirin et al. | Complex of model systems for supporting decisions made in managing blast-furnace smelting technology | |
| Shi et al. | Process Metallurgy and Genetic Algorithm Multi‐Objective Optimization of Blast Furnace Hearth Working State | |
| CN120386256B (en) | Coke oven integral energy saving method and system, electronic equipment and storage medium | |
| Saxena | Energy Management and Monitoring Systems | |
| CN119443729B (en) | Energy efficiency evaluation and intelligent diagnosis method for process industrial production system | |
| Wang et al. | Endpoint Prediction of Copper Converter Blowing Based on Artificial Bee Colony Algorithm and Regularized Extreme Learning Machine | |
| Liu et al. | Real-time dynamic estimation of carbon content in converter melt pool based on smelting mix data | |
| CN119940656B (en) | Steel industry steelmaking process optimization method, equipment and storage medium | |
| Saidmurodov et al. | Models of Operational Forecasting of Arc Furnace Energy Consumption Using Machine Learning Methods | |
| Jing et al. | Carbon Emission Forecasting Method for Steel Industry Based on Electric-Carbon Correlation Modeling | |
| Zhao et al. | A Multi-Label Prediction Model for Iron Ore Sintering Process Incorporating Time Features | |
| Leont’ev et al. | Mathematical modelling system for metallurgical enterprise: Operation and usability enhancement | |
| CN120258261B (en) | Precision coking coal blending method and system | |
| Zhang et al. | Improved back propagation neural network method for predicting sulfur content in hot metal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |