CN116306232A - Blast furnace energy consumption and carbon emission analysis method and system based on industrial big data - Google Patents
Blast furnace energy consumption and carbon emission analysis method and system based on industrial big data Download PDFInfo
- Publication number
- CN116306232A CN116306232A CN202310072939.8A CN202310072939A CN116306232A CN 116306232 A CN116306232 A CN 116306232A CN 202310072939 A CN202310072939 A CN 202310072939A CN 116306232 A CN116306232 A CN 116306232A
- Authority
- CN
- China
- Prior art keywords
- blast furnace
- energy consumption
- carbon emission
- data
- influence
- 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
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 158
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 157
- 238000005265 energy consumption Methods 0.000 title claims abstract description 156
- 238000004458 analytical method Methods 0.000 title claims abstract description 29
- 238000004519 manufacturing process Methods 0.000 claims abstract description 59
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000010801 machine learning Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 238000007418 data mining Methods 0.000 claims abstract description 8
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 230000002159 abnormal effect Effects 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 41
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 25
- 229910052742 iron Inorganic materials 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 12
- 238000010219 correlation analysis Methods 0.000 claims description 11
- 238000013210 evaluation model Methods 0.000 claims description 11
- 238000000513 principal component analysis Methods 0.000 claims description 10
- 238000000556 factor analysis Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000013079 data visualisation Methods 0.000 claims description 6
- 239000002994 raw material Substances 0.000 claims description 6
- 239000000571 coke Substances 0.000 claims description 4
- 239000007789 gas Substances 0.000 claims description 4
- 239000002893 slag Substances 0.000 claims description 4
- 238000012098 association analyses Methods 0.000 claims description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 239000000446 fuel Substances 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 239000000523 sample Substances 0.000 claims 3
- 239000000758 substrate Substances 0.000 claims 2
- 239000002817 coal dust Substances 0.000 claims 1
- 230000009467 reduction Effects 0.000 abstract description 6
- 238000004134 energy conservation Methods 0.000 abstract description 5
- 229910000831 Steel Inorganic materials 0.000 description 11
- 239000010959 steel Substances 0.000 description 11
- 239000002956 ash Substances 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 5
- 235000019580 granularity Nutrition 0.000 description 4
- 239000003245 coal Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 239000000843 powder Substances 0.000 description 2
- 241001449342 Chlorocrambe hastata Species 0.000 description 1
- 229910001341 Crude steel Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000010883 coal ash Substances 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computer Hardware Design (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a blast furnace energy consumption and carbon emission analysis method based on industrial big data, which comprises the following steps: s1, acquiring a historical data set in the blast furnace production process, and constructing a blast furnace production database; s2, based on a blast furnace production database, carrying out data processing and blast furnace index calculation, and carrying out missing value and abnormal value processing on the collected blast furnace raw data; calculating the energy consumption and the carbon emission of the blast furnace at the corresponding moment to form new data content, and forming a blast furnace energy consumption and carbon emission application data set with the processed data; s3, constructing a blast furnace energy consumption and carbon emission influence factor evaluation module based on the blast furnace energy consumption and carbon emission application data set and combining a data mining technology. The analysis method provided by the invention can intuitively reflect the current energy consumption and carbon emission influence factors from the data, establishes an influence factor optimizing model by combining a machine learning algorithm, and excavates the optimal range of the influence parameters under the aim of energy conservation and emission reduction of the blast furnace.
Description
Technical Field
The invention belongs to the technical field of analysis, evaluation and optimization of energy consumption and carbon emission in a blast furnace ironmaking process, and particularly relates to a method and a system for analyzing the energy consumption and the carbon emission of a blast furnace with industrial big data.
Background
The steel industry is an important pillar type industry for national economy development, and is also a large household with high energy consumption and high emission. According to data statistics, the energy consumption of the steel industry accounts for 15% of the total national energy consumption, and the carbon emission accounts for 13% -15% of the total national carbon emission. The energy-saving low-carbon transformation task of the steel industry is severe. The blast furnace ironmaking process is the most main component part in the long-flow production of steel, consumes a large amount of fossil energy and discharges a large amount of CO2 along with the production process, and according to data, the energy consumption of the blast furnace ironmaking process accounts for about 47% of the energy consumption of the whole-flow production of steel, and the CO2 discharge accounts for about 40% of the total-plant discharge, so that the energy-saving and emission-reducing spearhead in the steel industry is used for reducing the energy consumption and CO2 discharge of the blast furnace ironmaking process.
At present, the calculation method of the energy consumption and the carbon emission of the blast furnace process is mature, the statistical range of the energy consumption of the blast furnace process is defined in the energy consumption limit of the unit product of the crude steel production main process (GB 21256-2013) implemented in the 10 th month 1 of 2014 in the calculation of the energy consumption of the blast furnace ironmaking process, the content and the method of the calculation of the energy consumption of the blast furnace process are specified, and various energy refraction standard coal coefficient recommended values are provided for calculating the energy consumption of the blast furnace. Aiming at the calculation method of carbon emission in the steel industry, a plurality of versions are formed in China, and the method with the latest popularization time and the most extensive application at present is the part 5 of the requirements for accounting and reporting of greenhouse gas emission: iron and steel manufacturing enterprises (GB/T32151.5-2015), wherein accounting boundaries, accounting contents and specific methods in the iron and steel production process are specified, carbon emission calculation modes for the whole flow and each production process of the iron and steel industry are elaborated, carbon emission report templates and recommended emission factors of some common fossil fuels and production process substances are provided, and standards are provided for calculating carbon emissions for iron and steel production.
At present, the analysis method for exploring the energy consumption and the carbon emission of the blast furnace has certain implementation difficulty and limitation, for example, the mechanism in the production of the blast furnace is unclear, a large number of uncertain chemical reaction processes exist, and when the condition of the blast furnace fluctuates, the analysis result based on the mechanism of the blast furnace is poorer in accordance with the actual condition. It is difficult to directly quantify the degree of influence of each production parameter mechanically for blast furnace energy consumption and carbon emission analysis.
At present, the analysis of energy consumption and carbon emission of the blast furnace mainly focuses on input-output conditions in production index calculation, and influences on other production parameters of the blast furnace are found to be insufficient. The production of the blast furnace can be regarded as a 'black box model', the production parameters are numerous and disordered, in the analysis and judgment of the energy consumption and the carbon emission of the blast furnace, the influence degree of each production factor on the energy consumption and the carbon emission of the blast furnace is difficult to be quantitatively analyzed directly from the mechanism side, and the main factors influencing the energy consumption and the carbon emission of the blast furnace are difficult to be directly grasped on the premise of too many influence factors. Along with the daily production of the blast furnace, the energy consumption and carbon emission influencing factors can also change substantially along with the production condition, and how to accurately, timely and rapidly analyze the energy consumption and the carbon emission of the blast furnace becomes the main development direction of energy conservation and carbon reduction of the blast furnace nowadays.
Disclosure of Invention
First, the technical problem to be solved
In order to solve the problems of the prior art, the invention provides the method and the system for analyzing the energy consumption and the carbon emission of the blast furnace with industrial big data, which can intuitively reflect the current influence factors of the energy consumption and the carbon emission from the data, establish an influence factor optimizing model by combining a machine learning algorithm, and excavate the optimal range of the influence parameters under the aim of energy conservation and emission reduction of the blast furnace, thereby solving the technical problems that the conventional analysis method is difficult to implement, has large limitation and can not accurately, timely and rapidly analyze the relation between the energy consumption and the carbon emission of the blast furnace.
(II) technical scheme
In order to achieve the above purpose, the main technical scheme adopted by the invention comprises the following steps:
a blast furnace energy consumption and carbon emission analysis method based on industrial big data comprises the following steps:
s1, acquiring a historical data set in the blast furnace production process, and constructing a blast furnace production database;
the historical data comprise raw material parameters, operation parameters, furnace condition parameters and slag iron parameters in the operation and production of the blast furnace;
s2, based on a blast furnace production database, carrying out data processing and blast furnace index calculation, and carrying out missing value and abnormal value processing on the collected blast furnace raw data;
calculating the energy consumption and the carbon emission of the blast furnace at the corresponding moment to form new data content, and forming a blast furnace energy consumption and carbon emission application data set with the processed data;
s3, based on a blast furnace energy consumption and carbon emission application data set, a blast furnace energy consumption and carbon emission influence factor evaluation model is constructed by combining a data mining technology, influence correlation analysis is conducted on blast furnace energy consumption and carbon emission influence factor evaluation model parameters, and influence contribution grades are classified;
s4, acquiring main influence parameters of the energy consumption and the carbon emission of the blast furnace based on the influence factor evaluation model, and constructing a blast furnace energy consumption and carbon emission influence factor analysis model by combining a machine learning algorithm to obtain the influence quantity and the data visualization relation of the main influence factor change on the blast furnace energy consumption and the carbon emission;
s5, establishing a blast furnace energy consumption and carbon emission influence factor optimizing model through machine learning based on blast furnace energy consumption and carbon emission application data, a blast furnace energy consumption and carbon emission influence factor evaluating model and a blast furnace energy consumption and carbon emission influence factor analyzing model;
and performing unsupervised learning on the blast furnace production data based on the blast furnace energy consumption and carbon emission influence factor optimizing model, classifying the conditions of the lowest energy consumption and carbon emission of the blast furnace, and obtaining the optimal operation range of the main influence factors.
Preferably, the S1 further includes: invoking blast furnace production related parameter data based on a blast furnace production database;
the blast furnace production related parameter data mainly comprises raw material components, fuel physical components, blast furnace blast parameters and blast furnace produced slag-iron gas parameters.
Preferably, the S2 further includes: carrying out data processing on the data in the blast furnace production database;
the data processing mainly processes the data missing value and the data abnormal value;
for the missing values, a median filling method is adopted to complement the missing values;
the outlier is removed by using a box graph method.
Preferably, the step S3 further includes: based on the formed blast furnace energy consumption and carbon emission application data set, screening key influence factors of blast furnace energy consumption and carbon emission indexes by adopting an algorithm combining principal component analysis and ash content association analysis, and sorting according to the association degree of each influence factor to obtain an association sequence with large influence on blast furnace energy consumption and carbon emission degree in the current data parameters.
Preferably, the algorithm combining the principal component analysis and the ash correlation analysis comprises: determining an analysis array and a correlation coefficient;
determining a reference sequence and a comparison sequence, and selecting the energy consumption and carbon emission value of the blast furnace as a reference sequence, wherein the reference sequence is expressed as y= (y) 1 ,y 2 ,...,y n ) Comparing the series to obtain parameters of the blast furnace;
wherein the carbon content of coke, ash content of coal powder, blast air temperature, blast oxygen enrichment rate, blast pressure, molten iron temperature and the like are expressed as x i ＝(x i (1),x i (2),...,x i (n)(i＝1,2,...n)，
Then x i ＝(x i (1),x i (2),…,x i (n))(i＝1,2,…,n 2 ) And y= (y) 1 ,y 2 ,…,y n ) The correlation coefficient of (2) is:
wherein ρ e (0, + -infinity) is the resolution factor, the effect is to improve the significance between the correlation coefficients; typically ρ∈ (0, 1), typically ρ=0.5.
Preferably, the algorithm combining principal component analysis and ash correlation analysis further comprises: calculating the association degree;
the method for calculating the association degree usually adopts an average value method:
wherein, xi i (k) (k=1, 2, …, N) is the association sequence.
Preferably, the algorithm combining principal component analysis and ash correlation analysis further comprises: sorting the association degree;
correlation degree gamma of comparison sequence and reference sequence i (i＝1,2,…n 2 ) And sorting from large to small to obtain the association relation between the corresponding parameters and the energy consumption and the carbon emission.
Preferably, the S4 further includes:
and (3) obtaining the current association sequencing of the blast furnace energy consumption and the carbon emission according to the step (S3), carrying out data fitting analysis on main influence parameters by adopting a regression algorithm in machine learning to form influence quantities of the blast furnace energy consumption and the carbon emission caused by the change of the influence parameters, and constructing and forming an influence factor analysis model of the influence parameters, the blast furnace energy consumption and the carbon emission.
Preferably, the step S5 further includes:
based on the energy consumption and carbon emission conditions of the blast furnace, a machine learning k-means clustering algorithm is used in combination, after unsupervised learning is carried out, the actual energy consumption and carbon emission levels of the blast furnace are classified, and the optimal operation range of main influencing parameters is obtained through the technologies of data visualization, data classification and the like under the specified levels of low energy consumption and carbon emission.
The embodiment also provides a blast furnace energy consumption and carbon emission analysis system based on the industrial big data of the method according to the scheme, which at least comprises: the system comprises a data acquisition and processing module, a blast furnace energy consumption and carbon emission influence factor evaluation module, a blast furnace energy consumption and carbon emission influence factor analysis module and a blast furnace energy consumption and carbon emission influence factor optimizing module.
(III) beneficial effects
The beneficial effects of the invention are as follows:
on the premise of large data of blast furnace production industry, relevant data are collected to form a blast furnace production database, a blast furnace energy consumption and carbon emission application data set for preparing data mining is formed through data processing and index calculation, a blast furnace energy consumption and carbon emission influence factor analysis and evaluation model is built by combining a data mining technology, influence correlation analysis is carried out on factors of energy consumption and carbon emission from the blast furnace production data, and difficulty in mechanism analysis is avoided. The method comprises the steps of searching indexes with larger influence degree on blast furnace energy consumption and carbon emission in actual production, obtaining the influence quantity of the blast furnace energy consumption and the carbon emission of each index, intuitively reflecting the current influence factors of the energy consumption and the carbon emission from data, establishing an influence factor optimizing model by combining a machine learning algorithm, excavating the optimal range of influence parameters under the aim of energy conservation and emission reduction of the blast furnace, and providing optimization guidance for the blast furnace parameters.
Compared with the prior art, the scheme provided by the application starts from the data side, avoids a large amount of uncertainty in the blast furnace mechanism, more objectively knows the relation between the energy consumption and the carbon emission influence factors of the blast furnace equipment, and avoids the problem that the blast furnace parameters are difficult to be related to the blast furnace energy consumption and the carbon emission in mechanism. The machine learning algorithm of the blast furnace production data and the big data is fused, and the production condition of the blast furnace can be known to the greatest extent by combining a scientific calculation method, so that the actual evaluation of the influence factors of the blast furnace energy consumption and the carbon emission is accurately provided. Based on industrial data, the real running state of the lowest energy consumption and carbon emission of the current equipment is found by combining a data mining algorithm, the real optimal range of the influence parameters of the energy consumption and the carbon emission of the blast furnace is mined, the optimization direction of the blast furnace operation is provided, and a feasible scheme is provided for the energy-saving and carbon-reduction running of the blast furnace. The invention has simple realization, is practical and meets the application requirement.
Drawings
FIG. 1 is a schematic flow chart of a blast furnace energy consumption and carbon emission analysis method based on industrial big data;
FIG. 2 is a schematic flow chart of a data processing method of a blast furnace energy consumption and carbon emission analysis method based on industrial big data;
fig. 3 is a schematic diagram of the module configuration of the blast furnace energy consumption and carbon emission analysis system based on industrial big data.
Detailed Description
The invention will be better explained by the following detailed description of the embodiments with reference to the drawings.
As shown in fig. 1: the embodiment discloses a blast furnace energy consumption and carbon emission analysis method based on industrial big data, which is shown in fig. 1 and 2, and comprises the following steps:
s1, acquiring a historical data set in the blast furnace production process, and constructing a blast furnace production database, wherein the historical data comprises raw material parameters, operation parameters, furnace condition parameters and slag iron parameters in the blast furnace operation production. Collecting according to data points in actual production, and collecting all the collectable data in blast furnace production.
In practical application, based on a database of blast furnace production, relevant parameter data of blast furnace production is called, and mainly comprises raw material components, fuel physical property components, blast furnace blast parameters, blast furnace produced slag-iron gas parameters and the like, such as coke components and physical properties, coal powder components, sintered ore pellet components, blast furnace blast properties, molten iron slag components, blast furnace gas components, heat value and the like, wherein the data time granularity is in the four types of minutes, hours, groups and days.
S2, based on a database of blast furnace production, carrying out data processing and blast furnace index calculation, and carrying out missing value and abnormal value processing on the collected blast furnace raw data. And calculating the energy consumption and the carbon emission of the blast furnace at the corresponding moment, forming new data content, and forming a blast furnace energy consumption and carbon emission application data set with the processed data.
In detail, the data processing is performed on the blast furnace production database, and the data processing is required because of the existence of a lot of noise and error values during the collection of the instrument and the existence of errors during the manual recording. The data processing in this example is performed in a python environment, and mainly processes data missing values and data outliers. For the missing values, a median filling method is adopted to complement the missing values; the outlier is removed by using a box graph method.
For different time units on data acquisition, data frequency alignment and time-lag processing are performed, and in the example, the time granularity is divided into hours, shifts and days. And respectively summarizing the blast furnace production data under different time granularities.
And (3) calculating the energy consumption and carbon emission indexes of the blast furnace, calculating the energy consumption and carbon emission values of the blast furnace at the current time granularity according to input and output data of blast furnace production based on national calculation standards, storing the energy consumption and carbon emission values into an application data set of the energy consumption and carbon emission of the blast furnace, and providing basic preparation for data mining analysis and construction models.
S3, based on the application data set of the energy consumption and the carbon emission of the blast furnace, a factor evaluation model for influencing the energy consumption and the carbon emission of the blast furnace is built by combining a data mining technology, the parameters of the factor evaluation model for influencing the energy consumption and the carbon emission of the blast furnace are subjected to correlation analysis and weight classification, and main data factors influencing the energy consumption and the carbon emission of the blast furnace are explored.
In detail, based on the formed blast furnace energy consumption and carbon emission application data set, the key influencing factors of the blast furnace energy consumption and carbon emission indexes are screened by adopting an algorithm combining principal component analysis and ash content association analysis in the embodiment, and the association sequence with larger influencing blast furnace energy consumption and carbon emission degree in the current data parameters is obtained according to the association degree ranking of each influencing factor.
In detail, the algorithm combining principal component analysis and ash correlation analysis in this example includes:
(1) And determining an analysis array and calculating a relation coefficient. Determining a reference sequence and a comparison sequence, and selecting the energy consumption and carbon emission value of the blast furnace as a reference sequence, wherein the reference sequence is expressed as y= (y) 1 ,y 2 ,...,y n ) The comparative series are parameters of the blast furnace, such as coke carbon content, pulverized coal ash, blast air temperature, blast oxygen enrichment rate, blast pressure, molten iron temperature, etc., which represent x i ＝(x i (1),x i (2),...,x i (n) (i=1, 2, n.), then x i ＝(x i (1),x i (2),…,x i (n))(i＝1,2,…,n 2 ) And y= (y) 1 ,y 2 ,…,y n ) The correlation coefficient of (2) is:
wherein ρ e (0, + -infinity) is the resolution factor, the effect is to increase the significance between the correlation coefficients. Typically ρ∈ (0, 1), typically ρ=0.5.
(2) The association degree is calculated by adopting an average value method:
wherein, xi i (k) (k=1, 2, …, N) is the association sequence.
(3) And (5) sorting the association degree: correlation degree gamma of comparison sequence and reference sequence i (i＝1,2,…n 2 ) And sorting from large to small to obtain the association relation between the corresponding parameters and the energy consumption and the carbon emission.
S4, acquiring main influence parameters of the energy consumption and the carbon emission of the blast furnace based on the evaluation model of the influence factors of the energy consumption and the carbon emission of the blast furnace, constructing an analysis model of the influence factors of the energy consumption and the carbon emission of the blast furnace by combining a machine learning algorithm, acquiring the influence quantity relation and the data visualization relation of the change of the main influence factors on the energy consumption and the carbon emission of the blast furnace, and knowing the change of the energy consumption and the carbon emission of the blast furnace caused by the change of the actual influence factors.
In detail, the current blast furnace energy consumption and carbon emission association sequencing is obtained according to the step S3, data fitting analysis is carried out on main influence parameters by adopting a regression algorithm in machine learning, influence quantities of blast furnace energy consumption and carbon emission caused by influence parameter change are formed, and a blast furnace energy consumption and carbon emission influence factor analysis model is constructed and formed.
S5, establishing a blast furnace energy consumption and carbon emission influence factor optimizing model through machine learning based on blast furnace energy consumption and carbon emission application data, a blast furnace energy consumption and carbon emission influence factor evaluating model and a blast furnace energy consumption and carbon emission influence factor analyzing model;
and carrying out unsupervised learning on blast furnace production data based on a blast furnace energy consumption and carbon emission influence factor optimizing model, classifying the conditions of the lowest energy consumption and carbon emission of the blast furnace, obtaining the optimal operation range of main influence factors, and providing influence parameter optimizing guidance for energy conservation and carbon reduction of the blast furnace.
In detail, based on the condition of blast furnace energy consumption and carbon emission, a machine learning k-means clustering algorithm is used in combination, after unsupervised learning is carried out, the actual blast furnace energy consumption and carbon emission level are classified, and under the specified level of low energy consumption and carbon emission, the optimal operation range of main influencing parameters is obtained through the technologies of data visualization, data classification and the like. According to the actual operation and production conditions, the optimal parameter range of each influence factor is provided, and a feasible data basis is provided for achieving a good energy-saving and carbon reduction target.
In this embodiment, a system for analyzing energy consumption and carbon emission of a blast furnace based on industrial big data is also provided, as shown in fig. 3, and specific functions of the system include:
(1) The data acquisition and processing module: the method is particularly used for collecting the production data of the blast furnace, and a blast furnace energy consumption and carbon emission application data set is formed by processing the data and calculating the energy consumption and carbon emission indexes of the blast furnace;
(2) The blast furnace energy consumption and carbon emission influence factor evaluation module: based on the blast furnace energy consumption and carbon emission application data set, based on a blast furnace energy consumption and carbon emission influence factor evaluation model, searching an influence relation of model parameters on the blast furnace energy consumption and the carbon emission;
(3) The blast furnace energy consumption and carbon emission influence factor analysis module: the method is particularly used for analyzing the influence quantity brought by the influence factors of the energy consumption and the carbon emission of the blast furnace, and based on the analysis model of the influence factors of the energy consumption and the carbon emission of the blast furnace, the influence quantity relation of main influence factors on the energy consumption and the carbon emission of the blast furnace is explored;
(4) And a blast furnace energy consumption and carbon emission influence factor optimizing module: the method is particularly used for searching the optimal operation range of the influence parameters, searching the optimal operation range of each influence parameter under the optimal energy consumption and carbon emission conditions based on the optimization model of the influence factors of the energy consumption and the carbon emission of the blast furnace, and providing optimization guidance of the energy consumption and the carbon emission of the blast furnace.
The technical principles of the present invention have been described above in connection with specific embodiments, which are provided for the purpose of explaining the principles of the present invention and are not to be construed as limiting the scope of the present invention in any way. Other embodiments of the invention will be apparent to those skilled in the art from consideration of this specification without undue burden.
Claims (10)
1. The blast furnace energy consumption and carbon emission analysis method based on industrial big data is characterized by comprising the following steps of:
s1, acquiring a historical data set in the blast furnace production process, and constructing a blast furnace production database;
the historical data comprise raw material parameters, operation parameters, furnace condition parameters and slag iron parameters in the operation and production of the blast furnace;
s2, based on a blast furnace production database, carrying out data processing and blast furnace index calculation, and carrying out missing value and abnormal value processing on the collected blast furnace raw data;
calculating the energy consumption and the carbon emission of the blast furnace at the corresponding moment to form new data content, and forming a blast furnace energy consumption and carbon emission application data set with the processed data;
s3, based on a blast furnace energy consumption and carbon emission application data set, a blast furnace energy consumption and carbon emission influence factor evaluation model is constructed by combining a data mining technology, influence correlation analysis is conducted on blast furnace energy consumption and carbon emission influence factor evaluation model parameters, and influence contribution grades are classified;
s4, acquiring main influence parameters of the energy consumption and the carbon emission of the blast furnace based on a blast furnace energy consumption and carbon emission influence factor evaluation model, and constructing a blast furnace energy consumption and carbon emission influence factor analysis model by combining a machine learning algorithm to acquire influence quantity and data visualization relation of main influence factor change on the energy consumption and the carbon emission of the blast furnace;
s5, establishing a blast furnace energy consumption and carbon emission influence factor optimizing model through machine learning based on blast furnace energy consumption and carbon emission application data, a blast furnace energy consumption and carbon emission influence factor evaluating model and a blast furnace energy consumption and carbon emission influence factor analyzing model;
and performing unsupervised learning on the blast furnace production data based on the blast furnace energy consumption and carbon emission influence factor optimizing model, classifying the conditions of the lowest energy consumption and carbon emission of the blast furnace, and obtaining the optimal operation range of the main influence factors.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the S1 further includes: invoking blast furnace production related parameter data based on a blast furnace production database;
the blast furnace production related parameter data mainly comprises raw material components, fuel physical components, blast furnace blast parameters and blast furnace produced slag-iron gas parameters.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
the S2 further includes: carrying out data processing on the data in the blast furnace production database;
the data processing mainly processes the data missing value and the data abnormal value;
for the missing values, a median filling method is adopted to complement the missing values;
the outlier is removed by using a box graph method.
4. The method of claim 3, wherein the step of,
the step S3 further includes: based on the formed blast furnace energy consumption and carbon emission application data set, screening key influence factors of blast furnace energy consumption and carbon emission indexes by adopting an algorithm combining principal component analysis and ash content association analysis, and sorting according to the association degree of each influence factor to obtain an association sequence with large influence on blast furnace energy consumption and carbon emission degree in the current data parameters.
5. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
the algorithm combining the principal component analysis and the ash correlation analysis comprises: determining an analysis array and a correlation coefficient;
determining a reference sequence and a comparison sequence, and selecting the energy consumption and carbon emission value of the blast furnace as a reference sequence, wherein the reference sequence is expressed as y= (y) 1 ,y 2 ,...,y n ) Comparing the series to obtain parameters of the blast furnace;
wherein the coke carbon content, the ash content of the coal dust and the blast air temperatureThe oxygen enrichment rate, the blast pressure, the molten iron temperature and the like of the blast are expressed as x i ＝(x i (1),x i (2),...,x i (n)(i＝1,2,...n)，
Then x i ＝(x i (1),x i (2),…,x i (n))(i＝1,2,…,n 2 ) And y= (y) 1 ,y 2 ,…,y n ) The correlation coefficient of (2) is:
wherein ρ e (0, + -infinity) is the resolution factor, the effect is to improve the significance between the correlation coefficients; typically ρ∈ (0, 1), typically ρ=0.5.
6. The method of claim 5, wherein the step of determining the position of the probe is performed,
the algorithm combining principal component analysis and ash correlation analysis further comprises: calculating the association degree;
the method for calculating the association degree usually adopts an average value method:
wherein, xi i (k) (k=1, 2, …, N) is the association sequence.
7. The method of claim 6, wherein the step of providing the first layer comprises,
the algorithm combining principal component analysis and ash correlation analysis further comprises: sorting the association degree;
correlation degree gamma of comparison sequence and reference sequence i (i＝1,2,…n 2 ) And sorting from large to small to obtain the association relation between the corresponding parameters and the energy consumption and the carbon emission.
8. The method of claim 5, wherein the step of determining the position of the probe is performed,
the S4 further includes:
and (3) obtaining the current association sequencing of the blast furnace energy consumption and the carbon emission according to the step (S3), carrying out data fitting analysis on main influence parameters by adopting a regression algorithm in machine learning to form influence quantities of the blast furnace energy consumption and the carbon emission caused by influence parameter changes, and constructing and forming a blast furnace energy consumption and carbon emission influence factor analysis model.
9. The method of claim 5, wherein the step of determining the position of the probe is performed,
the step S5 further includes:
based on the energy consumption and carbon emission conditions of the blast furnace, a machine learning k-means clustering algorithm is used in combination, after unsupervised learning is carried out, the actual energy consumption and carbon emission levels of the blast furnace are classified, and the optimal operation range of main influencing parameters is obtained through the technologies of data visualization, data classification and the like under the specified levels of low energy consumption and carbon emission.
10. A blast furnace energy consumption and carbon emission analysis system based on industrial big data according to any one of claims 1-9, characterized in that,
at least comprises: the system comprises a data acquisition and processing module, a blast furnace energy consumption and carbon emission influence factor evaluation module, a blast furnace energy consumption and carbon emission influence factor analysis module and a blast furnace energy consumption and carbon emission influence factor optimizing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310072939.8A CN116306232A (en) | 2023-02-02 | 2023-02-02 | Blast furnace energy consumption and carbon emission analysis method and system based on industrial big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310072939.8A CN116306232A (en) | 2023-02-02 | 2023-02-02 | Blast furnace energy consumption and carbon emission analysis method and system based on industrial big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116306232A true CN116306232A (en) | 2023-06-23 |
Family
ID=86831440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310072939.8A Pending CN116306232A (en) | 2023-02-02 | 2023-02-02 | Blast furnace energy consumption and carbon emission analysis method and system based on industrial big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116306232A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808497A (en) * | 2024-03-01 | 2024-04-02 | 清华四川能源互联网研究院 | Electric power carbon emission abnormity detection module and method based on distance and direction characteristics |
-
2023
- 2023-02-02 CN CN202310072939.8A patent/CN116306232A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808497A (en) * | 2024-03-01 | 2024-04-02 | 清华四川能源互联网研究院 | Electric power carbon emission abnormity detection module and method based on distance and direction characteristics |
| CN117808497B (en) * | 2024-03-01 | 2024-05-14 | 清华四川能源互联网研究院 | Electric power carbon emission abnormity detection module and method based on distance and direction characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108830510B (en) | Power data preprocessing method based on mathematical statistics | |
| CN112699613B (en) | Multi-target integrated burdening optimization method, system, equipment and medium for iron making | |
| CN116306232A (en) | Blast furnace energy consumption and carbon emission analysis method and system based on industrial big data | |
| US20210065021A1 (en) | Working condition state modeling and model correcting method | |
| CN104593540A (en) | Method for evaluating energy efficiency in converter steelmaking process | |
| Ma et al. | Edge-cloud cooperation-driven smart and sustainable production for energy-intensive manufacturing industries | |
| CN111639801A (en) | Method and system for scoring furnace conditions of blast furnace | |
| CN113947241A (en) | Online coal quality database system for digital power plant construction | |
| CN114707120A (en) | Statistical modeling method for measuring and calculating carbon emission scale | |
| Shi et al. | Key issues and progress of industrial big data-based intelligent blast furnace ironmaking technology | |
| CN107942873A (en) | A kind of intelligent accounting of the operation cost of Furniture manufacture production line and monitoring method | |
| CN114066069A (en) | Combined weight byproduct gas generation amount prediction method | |
| Li et al. | Prediction Model for Vanadium Content in Vanadium and Titanium Blast Furnace Smelting Iron Based on Big Data Mining | |
| CN111798023B (en) | Comprehensive coke ratio prediction method in steelmaking sintering production | |
| CN111125082B (en) | Cement process parameter data analysis method based on association rule mining | |
| CN115204517A (en) | Method for predicting carbon emission in textile industry | |
| CN106651094B (en) | Enterprise energy efficiency evaluation method based on equivalent energy saving | |
| CN115392663A (en) | Data acquisition and processing method based on big data | |
| CN111639302B (en) | Sintering diagnosis system and method | |
| CN113359567A (en) | Energy consumption monitoring platform for key energy consumption unit | |
| CN111607417A (en) | Coking diagnostic system and method | |
| CN112270458A (en) | Energy refined management and control method and device, computer equipment and storage medium | |
| Shu et al. | A Novel EGM (1, 1) Model Based On Kernel And Degree Of Greyness And Its Application On Smog Prediction. | |
| CN116681331A (en) | Energy efficiency analysis method and device for heat treatment equipment, storage medium and computer equipment | |
| CN114611934A (en) | Iron and steel enterprise full-process carbon emission accounting method based on Gaussian distribution fitting and rolling correction |
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 |