Carbon emission monitoring method and device applied to steel production line, computer equipment, readable storage medium and program product

By constructing a carbon emission monitoring model and using material quality and temperature information, the problem of low accuracy of traditional carbon emission monitoring technology in steel production is solved, and efficient and accurate monitoring of carbon emissions in steel production lines and accurate equipment load status is achieved. control.

CN118966550APending Publication Date: 2024-11-15GUIZHOU POWER GRID CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411100529.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Traditional carbon emission monitoring technology has the problem of low accuracy in the steel production process, especially in extreme environments and special process conditions, which cannot accurately reflect the actual carbon emissions.

Method used

By obtaining material quality information and material temperature information in the intermediate process of steel production, a load monitoring model and a carbon emission monitoring model are constructed, and the target linear relationship between material quality and carbon emission is established using linear regression analysis and system correlation method, and then Achieve efficient and accurate monitoring of carbon emissions in steel production lines.

Benefits of technology

It improves the accuracy and stability of carbon emission monitoring, realizes accurate monitoring and management of the load status of steel production line equipment, and is suitable for various production environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966550A_ABST
    Figure CN118966550A_ABST
Patent Text Reader

Abstract

The invention relates to a carbon emission monitoring method and device applied to a steel production line, computer equipment, a readable storage medium and a program product, and relates to the technical field of carbon emission monitoring. The monitoring accuracy of the carbon emission can be improved. The method comprises the following steps: inputting material quality information and material temperature information corresponding to intermediate products passing through each electric device in a steel production intermediate flow into a pre-constructed load monitoring model to obtain power load information of each electric device; performing feature extraction on the material quality information to obtain data features of the material quality information, and performing correlation analysis on the data features to obtain a target linear relationship between the material quality information and the carbon emission; constructing a carbon emission monitoring model according to the historical power load information and the target linear relationship of each electric device in the steel generation intermediate process; and inputting the power load information and the material quality information into a carbon emission monitoring model to obtain the sum of carbon emission generated by the steel production line.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of carbon emission monitoring, and in particular to a carbon emission monitoring method, device, computer equipment, computer-readable storage medium and computer program product applied to a steel production line. Background Art

[0002] Steel is an important metal material, widely used in construction, machinery manufacturing, automobile and other industries. In the steel production process, monitoring the load of the production line is crucial to maintaining the efficient operation and reliability of the production line.

[0003] In traditional technology, multiple production processes in steel production require charcoal burning to discharge carbon. Currently, the carbon emission monitoring technologies commonly used by steel production enterprises include emission factor method and online monitoring method. The emission factor method relies on a general or average emission factor to estimate the carbon dioxide emissions of a specific process. However, this method often cannot accurately reflect the actual situation of each production link, especially when the enterprise uses special raw materials or technologies, its accuracy will be greatly reduced; for the online monitoring method, the accuracy of the online monitoring system may be affected by various factors in the production environment, such as extreme temperature, humidity and interference from pollutants, etc., resulting in the problem of low monitoring accuracy in both of the above two monitoring methods. Summary of the invention

[0004] Based on this, it is necessary to provide a carbon emission monitoring method, device, computer equipment, computer readable storage medium and computer program product for steel production lines to address the above technical problems.

[0005] In a first aspect, the present application provides a carbon emission monitoring method applied to a steel production line, comprising:

[0006] Obtaining material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, inputting the material quality information and the material temperature information into a pre-built load monitoring model, and obtaining the power load information of each electrical equipment;

[0007] Performing feature extraction on the material quality information to obtain data features of the material quality information, and performing correlation analysis on the data features to obtain a target linear relationship between the material quality information and carbon emissions;

[0008] Obtaining historical power load information of each of the power-consuming equipment in the intermediate process of steel production, and constructing a carbon emission monitoring model based on the historical power load information and the target linear relationship;

[0009] The power load information and the material quality information are input into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0010] In one embodiment, before inputting the material quality information and the material temperature information into a pre-built load monitoring model, the method further includes:

[0011] Obtain the historical load information of each of the electrical equipment, the historical material quality information and the historical material temperature information of each of the intermediate products; perform data cleaning and integration on the historical load information, the historical material quality information and the historical material temperature information to obtain a target data set; and construct the load monitoring model based on the target data set using a system association method.

[0012] In one embodiment, the use of the system association method to construct the load monitoring model according to the target data set includes:

[0013] Different types of data in the target data set are classified and identified according to preset standards, and preliminary association relationships between the various types of data are established; based on the preliminary association relationships, a cross-matching association query is performed on the target data set using a database query language to obtain association information contained in the target data set; incorrect associations are eliminated from the association information according to the logic of the steel production process to obtain target association information, and the load monitoring model is constructed based on the target association information.

[0014] In one embodiment, the performing correlation analysis on the data features to obtain the target linear relationship between the material quality information and the carbon emissions includes:

[0015] According to the data features, a linear regression model is fitted; according to the assumptions of the linear regression model, model diagnosis is performed on the linear regression model; if the model diagnosis passes, a linear regression analysis is performed on the data features based on the linear regression model to obtain the target linear relationship.

[0016] In one embodiment, constructing a carbon emission monitoring model according to the historical power load information and the target linear relationship includes:

[0017] According to the historical power load information and the target linear relationship, a training set and a test set are obtained; the training set is input into the carbon emission monitoring model to be trained for iterative training to obtain a preliminarily trained carbon emission monitoring model; the test set is used to test and tune the preliminarily trained carbon emission monitoring model until the preliminarily trained carbon emission monitoring model meets the accuracy and stability conditions, thereby obtaining the carbon emission monitoring model.

[0018] In one embodiment, the method further comprises:

[0019] Obtain evaluation values ​​of the carbon emission monitoring model under multiple preset evaluation indicators, and determine whether the evaluation values ​​meet the corresponding threshold conditions; when any of the evaluation values ​​does not meet the threshold conditions, determine the target model parameters corresponding to the current evaluation indicator, and adjust the target model parameters until the evaluation value of the current evaluation indicator meets the threshold conditions.

[0020] In a second aspect, the present application also provides a carbon emission monitoring device applied to a steel production line, comprising:

[0021] A load monitoring module is used to obtain material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, input the material quality information and the material temperature information into a pre-built load monitoring model, and obtain the power load information of each electrical equipment;

[0022] A relationship analysis module is used to extract features from the material quality information to obtain data features of the material quality information, perform correlation analysis on the data features, and obtain a target linear relationship between the material quality information and carbon emissions;

[0023] A model building module, used to obtain the historical power load information of each of the power-consuming equipment in the intermediate process of steel production, and to build a carbon emission monitoring model according to the historical power load information and the target linear relationship;

[0024] The carbon emission monitoring module is used to input the power load information and the material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0025] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0026] Obtain material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, input the material quality information and the material temperature information into a pre-constructed load monitoring model to obtain the power load information of each of the electrical equipment; perform feature extraction on the material quality information to obtain the data characteristics of the material quality information, perform correlation analysis on the data characteristics to obtain the target linear relationship between the material quality information and the carbon emissions; obtain the historical power load information of each of the electrical equipment in the intermediate process of steel production, and construct a carbon emission monitoring model based on the historical power load information and the target linear relationship; input the power load information and the material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0028] Obtain material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, input the material quality information and the material temperature information into a pre-constructed load monitoring model to obtain the power load information of each of the electrical equipment; perform feature extraction on the material quality information to obtain the data characteristics of the material quality information, perform correlation analysis on the data characteristics to obtain the target linear relationship between the material quality information and the carbon emissions; obtain the historical power load information of each of the electrical equipment in the intermediate process of steel production, and construct a carbon emission monitoring model based on the historical power load information and the target linear relationship; input the power load information and the material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0029] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0030] Obtain material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, input the material quality information and the material temperature information into a pre-constructed load monitoring model to obtain the power load information of each of the electrical equipment; perform feature extraction on the material quality information to obtain the data characteristics of the material quality information, perform correlation analysis on the data characteristics to obtain the target linear relationship between the material quality information and the carbon emissions; obtain the historical power load information of each of the electrical equipment in the intermediate process of steel production, and construct a carbon emission monitoring model based on the historical power load information and the target linear relationship; input the power load information and the material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0031] The carbon emission monitoring method, device, computer equipment, computer readable storage medium and computer program product applied to the steel production line, in the non-invasive load monitoring of electricity, obtains material quality information and material temperature information by weighing, measuring and recording the input of raw materials and the output of intermediate products / final products; then analyzes and processes the material quality information and material temperature information, finds out the relationship between each data and the equipment load state, and then reversely infers the equipment load state, thereby realizing accurate monitoring and evaluation of the load state of each major equipment in the steel production line. At the same time, a quality feature in steel production is introduced in carbon emission monitoring to realize "measure carbon by electricity-quality", analyzes the electricity-quality-carbon relationship of the steel enterprise in combination with the production process and carbon emission of the steel enterprise, and uses the learning algorithm to build a carbon emission monitoring model, and then uses the carbon emission monitoring model to monitor the carbon emissions generated by the steel production line, and finally efficiently and accurately measures the total carbon emissions generated by the steel production line, thereby improving the monitoring accuracy of carbon emissions and realizing accurate control and management of steel production line equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0033] FIG1 is an application environment diagram of a carbon emission monitoring method applied to a steel production line in one embodiment;

[0034] Figure 2 A schematic diagram of a process of a carbon emission monitoring method applied to a steel production line in one embodiment;

[0035] Figure 3 A schematic diagram of a flow chart of steps for constructing a load monitoring model in an embodiment;

[0036] Figure 4 is a schematic diagram of a process of non-intrusive power load monitoring in one embodiment;

[0037] Figure 5 A schematic diagram of the locations for obtaining quality and temperature in a raw material-milk steel production process in one embodiment;

[0038] Figure 6 A schematic diagram of a process for measuring a load state of an equipment in one embodiment;

[0039] Figure 7 A schematic diagram of the electricity-mass-carbon relationship of a steel production enterprise in one embodiment;

[0040] Figure 8 A schematic diagram of a process for establishing a carbon emission monitoring model in one embodiment;

[0041] Fig. 9 is a structural block diagram of a carbon emission monitoring device applied to a steel production line in one embodiment;

[0042] FIG. 10 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] The carbon emission monitoring method for a steel production line provided in an embodiment of the present application can be applied in an application environment as shown in FIG1 . The terminal communicates with the server via a network. The data storage system can store data that the server needs to process. The data storage system can be integrated on the server, or placed on a cloud or other network server.

[0045] Specifically, the carbon emission monitoring method applied to a steel production line provided in the embodiment of the present application can be executed by a server.

[0046] Exemplarily, the server obtains material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, inputs the material quality information and material temperature information into a pre-built load monitoring model, and obtains the power load information of each electrical equipment; the server extracts features from the material quality information to obtain data features of the material quality information, performs correlation analysis on the data features, and obtains the target linear relationship between the material quality information and carbon emissions; the server obtains historical power load information of the electrical equipment in each process flow, and constructs a carbon emission monitoring model based on the historical power load information and the target linear relationship; the server inputs the power load information and material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0047] In the application environment shown in FIG1 , the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers. The server may be implemented as an independent server or a server cluster consisting of multiple servers.

[0048] In one embodiment, Figure 2 As shown, a carbon emission monitoring method applied to a steel production line is provided, and the method is applied to the server in FIG1 as an example for explanation, including the following steps:

[0049] Step S201, obtain material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, input the material quality information and material temperature information into a pre-built load monitoring model, and obtain the power load information of each electrical equipment.

[0050] Among them, the raw materials in this scheme can be coal, iron ore and limestone, etc., the intermediate products can be pig iron and steel ingots, etc., and the final product can be rolled steel.

[0051] Among them, the material quality information includes the quality of the material when it is input into the device, the quality of the material when the device is output, and the change in quality; the material temperature information includes the temperature of the material when it is input into the device, the temperature of the material when the device is output, and the change in temperature.

[0052] Specifically, the server obtains the material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, inputs the material quality information and material temperature information into a pre-built load monitoring model, and obtains the power load information of each electrical equipment output by the load monitoring model.

[0053] Step S202, extracting features from the material quality information to obtain data features of the material quality information, performing correlation analysis on the data features to obtain a target linear relationship between the material quality information and carbon emissions.

[0054] Among them, the method of correlation analysis can be linear regression analysis, which can be used to study the linear relationship between independent variables (or predictors) and dependent variables.

[0055] Specifically, the server extracts features of the material quality information, obtains the data features of the material quality information by reducing the dimension of the data set, and fits a linear regression model based on the data features. According to the assumptions of the linear regression model, the linear regression model is diagnosed. If the model diagnosis passes, a linear regression analysis is performed on the data features based on the linear regression model to obtain the target linear relationship between the material quality information and carbon emissions.

[0056] Step S203, obtaining the historical power load information of the power-consuming equipment in each process flow, and constructing a carbon emission monitoring model based on the historical power load information and the target linear relationship.

[0057] Among them, the carbon emission monitoring model can be an electricity-quality-carbon monitoring model.

[0058] Specifically, the server obtains the historical power load information of electrical equipment in each process flow, and obtains a training set and a test set based on the historical power load information and the target linear relationship; then the training set is input into the carbon emission monitoring model to be trained for iterative training to obtain a preliminarily trained carbon emission monitoring model; and then the test set is used to test and tune the preliminarily trained carbon emission monitoring model until the preliminarily trained carbon emission monitoring model meets the accuracy and stability conditions, thereby obtaining a carbon emission monitoring model.

[0059] Step S204, inputting the power load information and material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0060] The power load information includes, but is not limited to, the current, voltage and power of each electrical equipment in the steel production line.

[0061] Specifically, the server inputs the power load information and material quality information into the carbon emission monitoring model, and obtains the total carbon emissions generated by the steel production line output by the carbon emission monitoring model.

[0062] The above carbon emission monitoring method applied to the steel production line, in the non-invasive load monitoring of electricity, obtains material quality information and material temperature information by weighing, measuring and recording the input of raw materials and the output of intermediate products / final products; then analyzes and processes the material quality information and material temperature information, finds out the relationship between each data and the equipment load state, and then reversely infers the equipment load state, thereby realizing accurate monitoring and evaluation of the load state of each major equipment in the steel production line. At the same time, a quality feature in steel production is introduced in carbon emission monitoring to realize "measure carbon by electricity-quality", analyzes the electricity-quality-carbon relationship of the steel enterprise in combination with the production process and carbon emission of the steel enterprise, and uses the learning algorithm to build a carbon emission monitoring model, and then uses the carbon emission monitoring model to monitor the carbon emissions generated by the steel production line, and finally efficiently and accurately measures the total carbon emissions generated by the steel production line, thereby improving the monitoring accuracy of carbon emissions and realizing accurate control and management of steel production line equipment.

[0063] In one embodiment, if Figure 3 As shown, before inputting the material quality information and the material temperature information into the pre-built load monitoring model, the method of the present application further includes the following steps:

[0064] Step S301, obtaining historical load information of each electrical device, historical material quality information of each intermediate product, and historical material temperature information.

[0065] Step S302 , cleaning and integrating historical load information, historical material quality information and historical material temperature information to obtain a target data set.

[0066] Step S303: construct a load monitoring model based on the target data set using a system association method.

[0067] The data cleaning process includes eliminating duplicate and abnormal data, and completing missing data.

[0068] Among them, the system association method is a system engineering methodology used to deal with the relationships and interactions between complex systems and their components. It emphasizes how multiple independent systems work together to achieve larger system goals.

[0069] Specifically, the server obtains the historical load information of each electrical equipment, the historical material quality information and the historical material temperature information of each intermediate product; cleans, classifies and integrates the historical load information, the historical material quality information and the historical material temperature information to obtain the target data set; classifies and identifies different types of data in the target data set according to preset standards, and establishes preliminary association relationships between various types of data; based on the preliminary association relationships, uses the database query language to perform cross-matching association queries on the target data set to obtain the association information contained in the target data set; eliminates erroneous associations in the association information according to the logic of the steel production process to obtain target association information, and builds a load monitoring model based on the target association information.

[0070] In this embodiment, by using the system association method, a load monitoring model is quickly and accurately constructed according to the target data set, which helps to obtain the power load information of each electrical device more accurately.

[0071] In one embodiment, the steel production process consists of four parts, namely, sintering / pelletizing process, ironmaking process, steelmaking process and steel rolling process. Figure 4 As shown, there are quality and temperature differences in the product input / output in each link of the entire process. This solution uses two-color temperature measurement technology to measure the temperature information of each product and uses visual weighing technology to collect the quality information of each product. After measuring and collecting physical quantities such as product input, output quality and temperature of each production process of the steel production line, the present invention also combines the system association method to establish a monitoring model M for data analysis to infer the power load of each electrical equipment in the steel production line. The system realizes data collection, transmission and processing through statistical association, and then provides power load monitoring results.

[0072] In one embodiment, if Figure 5 As shown, the production process from raw materials to rolled steel, in this process the quality that the present invention needs to obtain ( Figure 5 mn) and temperature ( Figure 5 The data information of (Tn) includes raw materials (such as coal, iron ore and limestone), intermediate products (such as pig iron, steel ingots) and the final product (mild steel).

[0073] After the above process, the data relationship between equipment load, material mass and material temperature will be obtained, which can be expressed by the formula:

[0074]

[0075] in refers to the power load status of device x, They represent the mass of the material input to device x, the mass of the material output from device x, the temperature of the material input to device x, and the temperature of the material output from device x. This indicates the relationship between the material physical quantity of equipment x and the equipment power load discovered by the system association method. In production, after receiving the quality data of the visual weighing and the temperature data of the double-sided thermometer, the system can output the load status of equipment x according to the stored association information (such as Figure 6 as shown).

[0076] In one embodiment, CO2 emissions in the steel production process can be roughly divided into three parts. The first part is the production process emissions, which are mainly the carbon dioxide produced by the decomposition of carbonate materials and the oxidation of carbon during blast furnace smelting and converter steelmaking; the second part is the fuel combustion emissions. In the blast furnace and converter process, the combustion of coke and other fuels generates a lot of heat and releases carbon dioxide; the third part is indirect emissions, which are the carbon dioxide emissions generated by the consumption of electricity used in the production process, especially the electricity used in the refining and continuous casting processes. The sintering / pelletizing process mainly provides the necessary heat by burning fuels such as coal, so a large amount of CO2 emissions are directly generated. In the ironmaking process, the combustion of coke is a direct source of carbon emissions. In the steelmaking process, the use of fuel in the converter process leads to direct carbon emissions, while the electric furnace mainly relies on electricity, and its carbon emissions mainly depend on the source of electricity. The carbon emissions of the steel rolling process are also mainly related to the source of electricity.

[0077] In the steel production process, from iron ore to final steel, this solution introduces a weighing link in non-invasive load monitoring, which can accurately understand the conversion efficiency and material loss of raw materials. Generally speaking, carbon emission calculations are usually based on the energy consumption (such as electricity, coal, and natural gas) and the chemical composition of raw materials in the production process. By knowing the weight of materials at each stage, the carbon emissions corresponding to fuel combustion and electricity consumption, as well as the carbon emissions directly generated through chemical reaction processes, can be calculated more accurately. Introducing the weighing of iron ore, sintered ore, molten iron, crude steel, and finished steel, using their weight as an input variable, as a variable and feature extraction of the electric-carbon model, and thus exploring their impact and related factors in the carbon emission process is a new attempt.

[0078] In one embodiment, if Figure 7 As shown in the figure, the electricity-quality-carbon relationship of steel enterprises is analyzed by studying the production process of steel enterprises and their electricity consumption, carbon emissions, etc.

[0079] Process the collected quality data. First, preprocess the collected data and convert the data into a standard format to reduce the impact of deviations between data of different magnitudes. Identify and process or eliminate outliers to ensure data quality. The second step is feature extraction. By reducing the dimension of the data set and extracting the most important features, it helps to reduce computational complexity and improve model efficiency. Then perform correlation analysis. Linear regression analysis can be used to preliminarily analyze the linear relationship between weight data and carbon emissions. Finally, optimize variables and modeling. Use the random forest algorithm for feature importance assessment to identify the factors that have the greatest impact on carbon emissions. Based on the above model, use algorithms such as genetic algorithms and particle swarm optimization to find the optimal variable settings in the production process.

[0080] The establishment of the electricity-quality-carbon monitoring model,based on the above analysis of the electricity-quality-carbon relationship of steel enterprises,,this plan will construct single-sample and multi-sample electricity-carbon models respectively.

[0081] The first step is variable analysis and sample processing: the input variables of the regression model are the carbonate decomposition emission factor in clinker production, the electricity emission factor in clinker production, the proportion of electricity consumption in the clinker section in the total electricity consumption of the plant, the steel clinker output ratio and the quality of steel materials, and the output variable is the electric carbon index.

[0082] Correlation analysis: Pearson correlation coefficient is used to quantify the linear correlation between variables. Values ​​close to 1 or -1 indicate strong correlation, and values ​​close to 0 indicate no correlation. For nonlinear relationships, Spearman rank correlation coefficient is used for analysis. In this method, correlation analysis is performed on the final variables of single-sample daily data and multi-sample annual data. The relationship between the electric carbon index and the carbonate decomposition emission factor in clinker production, the electricity emission factor for clinker production, the proportion of electricity consumption in the clinker section in the total electricity consumption of the plant, the ratio of steel clinker production, and the quality of steel materials.

[0083] Sample processing: Based on the data random splitting function of mathematical analysis software, 70% of the sample data are selected as the training set and 30% of the sample data are selected as the test set.

[0084] Regression analysis: The following regression methods are used for the prediction of the electricity-quality-carbon model: full subset regression model, ridge regression model, and elastic network model. Support vector machine model and neural network model are complex regression models. By building prediction models on the training set, predicting on the test set, and comparing the deviation between the predicted value and the true value of the test set, the quality of the model is judged, and the optimal model is obtained from multiple prediction models.

[0085] Model evaluation: The evaluation index of the regression algorithm mainly measures the closeness between the model prediction value and the true value. This paper uses three statistical indicators to evaluate and analyze the fitting results of the regression model: root mean square error (RMSE), mean absolute error (MAE) and goodness of fit ( ); The closer RMSE and MAE are to 0, the higher the prediction accuracy; The closer it is to 1, the better the fit.

[0086] The specific implementation process is as follows Figure 8 As shown in the figure, a single-sample daily electricity-quality-carbon monitoring model is established to monitor the electricity-quality-carbon emission performance of a steel plant in daily operations. Daily data of a single steel plant is collected, including but not limited to electricity consumption, raw material consumption, product output and possible carbon emissions. A multi-sample annual electricity-quality-carbon monitoring model is established to evaluate and compare the electricity-quality-carbon emission performance of multiple steel plants within a certain time period (usually one year). In addition to analyzing the correlation between variables, cluster analysis may also be performed to identify sample groups with similar electricity-carbon emission characteristics. More complex models are selected in the model selection and training process. For example, support vector machine models and neural network models are used to handle the complexity of multi-sample data. Multi-sample data sets are used for cross-validation to ensure the generalization ability of the model. Regularly evaluate and monitor the carbon emission effects after optimization and adjustment. Compare the carbon emission data before and after optimization to analyze the significance and sustainability of the optimization effect. Make necessary adjustments and improvements. In addition, a long-term carbon emission monitoring and management mechanism is established to continuously track the trend of carbon emission data changes and provide timely feedback on the carbon emission performance of enterprises. Through regular data analysis and reporting, problems can be discovered in a timely manner and corresponding measures can be taken to make adjustments and improvements.

[0087] Compared with the existing technical solutions, this technical solution has the following beneficial effects:

[0088] 1. Compared with the existing non-intrusive load monitoring, this solution does not need to collect power data under the dedicated transformer of the production line by measurement. It only needs to collect the relevant physical quantities of the product to obtain the load status of the equipment.

[0089] 2. Compared with the existing non-intrusive load monitoring, this solution can determine whether the equipment is operating under optimal conditions based on quality data. For example, if the thickness, width, and surface quality of the output steel do not meet the standards, it may mean that the mill load is unevenly distributed or too large.

[0090] 3. Compared with the existing non-intrusive load monitoring, this solution can analyze the efficiency of the cooling system and the utilization rate of thermal energy through temperature data, and then guide the improvement of equipment load devices.

[0091] 4. In terms of fault diagnosis, this solution can promptly detect equipment abnormalities through abnormal product quality and temperature, such as wear, deformation or other problems that cause load abnormalities in the equipment, so that potential equipment failure points can be located through reverse analysis.

[0092] 5. Existing technical solutions cannot accurately reflect the actual situation of each production link, especially when enterprises use special raw materials or technologies, their accuracy will be greatly reduced. This solution can provide more accurate carbon emission monitoring.

[0093] 6. This proposal proposes a method that uses steel weight as an intermediate quantity in the basic electric-carbon model, providing a real-time carbon emission monitoring technology.

[0094] 7. This solution is based on a non-invasive load electricity-carbon emission monitoring model. It monitors the electricity load and carbon emissions by introducing physical characteristics such as steel quality in steel production, thereby realizing "measuring carbon by electricity-quality", effectively combining the production process of steel enterprises, and achieving the purpose of monitoring electricity-carbon emissions in each link.

[0095] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiment of the present application also provides a carbon emission monitoring device applied to a steel production line for implementing the above-mentioned carbon emission monitoring method applied to a steel production line. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the carbon emission monitoring device applied to a steel production line provided below can refer to the above-mentioned limitations on the carbon emission monitoring method applied to a steel production line, and will not be repeated here.

[0097] In an exemplary embodiment, Fig. 9 As shown, a carbon emission monitoring device applied to a steel production line is provided, comprising:

[0098] The load monitoring module 901 is used to obtain the material quality information and material temperature information corresponding to the intermediate products passing through each power-consuming device in the intermediate process of steel production, input the material quality information and material temperature information into the pre-built load monitoring model, and obtain the power load information of each power-consuming device;

[0099] The relationship analysis module 902 is used to extract features of the material quality information, obtain data features of the material quality information, perform correlation analysis on the data features, and obtain a target linear relationship between the material quality information and carbon emissions;

[0100] The model building module 903 is used to obtain the historical power load information of the power-consuming equipment in each process flow, and build a carbon emission monitoring model according to the historical power load information and the target linear relationship;

[0101] The carbon emission monitoring module 904 is used to input the power load information and material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

[0102] In one embodiment, the carbon emission monitoring device applied to a steel production line also includes a system association module, which is used to obtain historical load information of each electrical equipment, historical material quality information and historical material temperature information of each intermediate product; perform data cleaning and integration on the historical load information, historical material quality information and historical material temperature information to obtain a target data set; and use the system association method to construct a load monitoring model based on the target data set.

[0103] In one embodiment, the system association module is also used to classify and identify different types of data in the target data set according to preset standards, and establish preliminary association relationships between the various types of data; based on the preliminary association relationships, use the database query language to perform a cross-matching association query on the target data set to obtain the association information contained in the target data set; according to the logic of the steel production process, the association information is erroneously eliminated to obtain the target association information, and a load monitoring model is constructed based on the target association information.

[0104] In one embodiment, the relationship analysis module 902 is also used to fit a linear regression model according to data features; perform model diagnosis on the linear regression model according to the assumptions of the linear regression model; and when the model diagnosis passes, perform linear regression analysis on the data features based on the linear regression model to obtain the target linear relationship.

[0105] In one embodiment, the model building module 903 is also used to obtain a training set and a test set based on historical power load information and a target linear relationship; input the training set into the carbon emission monitoring model to be trained for iterative training to obtain a preliminarily trained carbon emission monitoring model; use the test set to test and tune the preliminarily trained carbon emission monitoring model until the preliminarily trained carbon emission monitoring model meets the accuracy and stability conditions, thereby obtaining a carbon emission monitoring model.

[0106] In one embodiment, the carbon emission monitoring device applied to a steel production line also includes a model adjustment module, which is used to obtain the evaluation value of the carbon emission monitoring model under multiple preset evaluation indicators, and determine whether the evaluation value meets the corresponding threshold conditions; if any evaluation value does not meet the threshold conditions, determine the target model parameters corresponding to the current evaluation indicator, and adjust the target model parameters until the evaluation value of the current evaluation indicator meets the threshold conditions.

[0107] Each module in the carbon emission monitoring device for steel production line can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0108] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG10. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a carbon emission monitoring method applied to a steel production line is implemented.

[0109] Those skilled in the art will understand that the structure shown in FIG. 10 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0110] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0111] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0112] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0113] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0114] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0115] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0116] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A carbon emission monitoring method applied to a steel production line, characterized in that: The method comprises: Obtaining material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, inputting the material quality information and the material temperature information into a pre-built load monitoring model to obtain the power load information of each electrical equipment; Performing feature extraction on the material quality information to obtain data features of the material quality information, and performing correlation analysis on the data features to obtain a target linear relationship between the material quality information and carbon emissions; Obtaining historical power load information of each of the power-consuming equipment in the intermediate process of steel production, and constructing a carbon emission monitoring model based on the historical power load information and the target linear relationship; The power load information and the material quality information are input into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

2. The method according to claim 1, characterized in that Before inputting the material quality information and the material temperature information into a pre-built load monitoring model, the method further includes: Obtaining historical load information of each of the electrical equipment, historical material quality information and historical material temperature information of each of the intermediate products; Performing data cleaning and integration on the historical load information, the historical material quality information, and the historical material temperature information to obtain a target data set; The load monitoring model is constructed according to the target data set by using a system association method.

3. The method according to claim 2, characterized in that The method of using the system association method to construct the load monitoring model according to the target data set includes: Classifying and identifying different types of data in the target data set according to preset standards, and establishing preliminary association relationships between the different types of data; According to the preliminary association relationship, a cross-matching association query is performed on the target data set using a database query language to obtain association information contained in the target data set; According to the logic of the steel production process, the association information is erroneously eliminated to obtain target association information, and the load monitoring model is constructed based on the target association information.

4. The method according to claim 1, characterized in that: The performing correlation analysis on the data features to obtain a target linear relationship between the material quality information and the carbon emissions includes: According to the data characteristics, a linear regression model is fitted; Performing model diagnosis on the linear regression model according to the assumptions of the linear regression model; When the model diagnosis passes, a linear regression analysis is performed on the data features based on the linear regression model to obtain the target linear relationship.

5. The method according to claim 1, characterized in that The step of constructing a carbon emission monitoring model according to the historical power load information and the target linear relationship includes: According to the historical power load information and the target linear relationship, a training set and a test set are obtained; Inputting the training set into the carbon emission monitoring model to be trained for iterative training to obtain a preliminarily trained carbon emission monitoring model; The test set is used to test and tune the initially trained carbon emission monitoring model until the initially trained carbon emission monitoring model meets accuracy and stability conditions, thereby obtaining the carbon emission monitoring model.

6. The method according to claim 5, characterized in that The method further comprises: Obtaining evaluation values ​​of the carbon emission monitoring model under multiple preset evaluation indicators, and determining whether the evaluation values ​​meet corresponding threshold conditions; In the case that any of the evaluation values ​​does not meet the threshold condition, a target model parameter corresponding to the current evaluation indicator is determined, and the target model parameter is adjusted until the evaluation value of the current evaluation indicator meets the threshold condition.

7. A carbon emission monitoring device applied to a steel production line, characterized in that: The device comprises: A load monitoring module is used to obtain material quality information and material temperature information corresponding to the intermediate products passing through each electrical equipment in the intermediate process of steel production, input the material quality information and the material temperature information into a pre-built load monitoring model, and obtain the power load information of each electrical equipment; A relationship analysis module is used to extract features from the material quality information to obtain data features of the material quality information, perform correlation analysis on the data features, and obtain a target linear relationship between the material quality information and carbon emissions; A model building module, used to obtain the historical power load information of each of the power-consuming equipment in the intermediate process of steel production, and to build a carbon emission monitoring model according to the historical power load information and the target linear relationship; The carbon emission monitoring module is used to input the power load information and the material quality information into the carbon emission monitoring model to obtain the total carbon emissions generated by the steel production line.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.