CN109252009A - BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine - Google Patents
BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine Download PDFInfo
- Publication number
- CN109252009A CN109252009A CN201811382179.6A CN201811382179A CN109252009A CN 109252009 A CN109252009 A CN 109252009A CN 201811382179 A CN201811382179 A CN 201811382179A CN 109252009 A CN109252009 A CN 109252009A
- Authority
- CN
- China
- Prior art keywords
- manganese content
- data
- learning machine
- extreme learning
- regularization
- 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
- PWHULOQIROXLJO-UHFFFAOYSA-N Manganese Chemical compound [Mn] PWHULOQIROXLJO-UHFFFAOYSA-N 0.000 title claims abstract description 79
- 229910052748 manganese Inorganic materials 0.000 title claims abstract description 79
- 239000011572 manganese Substances 0.000 title claims abstract description 79
- 238000009628 steelmaking Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 21
- 230000004913 activation Effects 0.000 claims abstract description 8
- 229910000677 High-carbon steel Inorganic materials 0.000 claims description 30
- 229910000954 Medium-carbon steel Inorganic materials 0.000 claims description 30
- 229910000831 Steel Inorganic materials 0.000 claims description 18
- 239000010959 steel Substances 0.000 claims description 18
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 16
- 229910052742 iron Inorganic materials 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 6
- 238000003723 Smelting Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 claims description 3
- 239000003795 chemical substances by application Substances 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 229910000514 dolomite Inorganic materials 0.000 claims description 3
- 239000010459 dolomite Substances 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000036284 oxygen consumption Effects 0.000 claims description 3
- DPTATFGPDCLUTF-UHFFFAOYSA-N phosphanylidyneiron Chemical compound [Fe]#P DPTATFGPDCLUTF-UHFFFAOYSA-N 0.000 claims description 3
- 229910052717 sulfur Inorganic materials 0.000 claims description 3
- 239000011593 sulfur Substances 0.000 claims description 3
- 235000008733 Citrus aurantifolia Nutrition 0.000 claims description 2
- 235000011941 Tilia x europaea Nutrition 0.000 claims description 2
- 239000004571 lime Substances 0.000 claims description 2
- 239000000523 sample Substances 0.000 claims 11
- 239000013068 control sample Substances 0.000 claims 1
- 238000013480 data collection Methods 0.000 claims 1
- BZDIAFGKSAYYFC-UHFFFAOYSA-N manganese;hydrate Chemical compound O.[Mn] BZDIAFGKSAYYFC-UHFFFAOYSA-N 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 11
- 238000007619 statistical method Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- DALUDRGQOYMVLD-UHFFFAOYSA-N iron manganese Chemical compound [Mn].[Fe] DALUDRGQOYMVLD-UHFFFAOYSA-N 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 229910000975 Carbon steel Inorganic materials 0.000 description 1
- 238000005275 alloying Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 238000009865 steel metallurgy Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C5/00—Manufacture of carbon-steel, e.g. plain mild steel, medium carbon steel or cast steel or stainless steel
- C21C5/28—Manufacture of steel in the converter
-
- 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/20—Recycling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Materials Engineering (AREA)
- Organic Chemistry (AREA)
- Metallurgy (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- Carbon Steel Or Casting Steel Manufacturing (AREA)
Abstract
The present invention proposes the BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine, comprising the following steps: the selection of the input variable of regularization extreme learning machine, normalized, constructs regularization extreme learning machine and carries out the prediction of BOF Steelmaking Endpoint manganese content by regularization extreme learning machine the pretreatment of sample data；The present invention predicts BOF Steelmaking Endpoint manganese content by regularization extreme learning machine, the biasing of the input weight and hidden layer of adjustment network is not needed in the training process, hidden layer node number, regularization coefficient and the activation primitive that network need to only be arranged can generate unique optimal solution, and the model training speed is fast, precision of prediction is high, adaptability is preferable, this method measurement adaptability is good simultaneously, the training time is short, is not easy to fall into local optimum, can significantly improve the precision of prediction and arithmetic speed of BOF Steelmaking Endpoint manganese content.
Description
Technical field
The present invention relates to field of steel metallurgy, more particularly to the BOF Steelmaking Endpoint manganese based on regularization extreme learning machine contains
Measure prediction technique.
Background technique
Pneumatic steelmaking is current steel-making side most important in the world as link highly important in Steel Production Flow Chart
Method.In converter steelmaking process, if being able to achieve the accurate and quick prediction to endpoint molten steel manganese content, operation can be improved
The accuracy that personnel judge tapping, and the efficiency of steel alloying operation out, so that production cost is reduced, raising molten steel matter
Amount.Regularization refers in linear algebraic process, ill-posed problem be usually defined by one group of linear algebraic equation, and this
Group equation group is typically derived from the ill-posed inverse problem of very big conditional number.Extreme learning machine is a kind of based on feed forward neural
The machine learning algorithm of network, being mainly characterized by hidden layer node parameter can be random or given by man and does not need to adjust
Whole, learning process only needs to calculate output weight.
Currently, the prediction technique of BOF Steelmaking Endpoint manganese content mainly include statistical method and with non-statistical method,
Statistical method includes: linear regression, nonlinear regression etc., and non-statistical method includes: expert system, BP neural network etc..
The adaptability and generalization ability of BOF Steelmaking Endpoint manganese content prediction model based on statistical method foundation are weaker and certain
Statistical method is established using thermodynamics and material balance from pair on the basis of based on sublance sampling analysis molten steel manganese content
Rifle is sampled to the manganese content prediction model of blowing end point, higher cost, and is only applicable to the converter equipped with sublance；And based on non-
The BOF Steelmaking Endpoint manganese content prediction model of statistical method has stronger adaptability and generalization ability, due to influencing to make steel
The factor of terminal manganese content is numerous, and has stronger non-linear relation between each influence factor and terminal manganese content, artificial mind
It can be very good to solve the problems, such as this through the stronger None-linear approximation ability of network, BP neural network is at present using relatively broad
One of neural network, but the model established based on this method is needed to consume a large amount of time in training process, easily falls into office
Portion's optimal value and training process need to be arranged a large amount of network training parameter, and precision of prediction is low, it is difficult to rapidly, right in time
BOF Steelmaking Endpoint manganese content is accurately predicted, the high-efficiency reform of iron and steel enterprise's high-quality steel is unfavorable for.Therefore, this hair
Bright BOF Steelmaking Endpoint manganese content prediction technique of the proposition based on regularization extreme learning machine, to solve deficiency in the prior art
Place.
Summary of the invention
In view of the above-mentioned problems, the present invention predicts BOF Steelmaking Endpoint manganese content by regularization extreme learning machine,
The biasing for not needing the input weight and hidden layer of adjustment network in the training process, need to only be arranged the hiding node layer of network
Number, regularization coefficient and activation primitive can generate unique optimal solution, and the model training speed is fast, precision of prediction is high,
Adaptability is preferable, while this method measurement adaptability is good, the training time is short, is not easy to fall into local optimum, can significantly improve
The precision of prediction and arithmetic speed of BOF Steelmaking Endpoint manganese content.
The present invention proposes the BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine, including following step
It is rapid:
Step 1: the selection of the input variable of regularization extreme learning machine
The medium and high carbon steel historical data of converter smelting is acquired, and determines that influencing BOF Steelmaking Endpoint manganese content influences
Set of factors；
Step 2: the pretreatment of sample data
The influence factor data of BOF Steelmaking Endpoint manganese content are acquired, then the sample data of acquisition are carried out pre-
Processing, determines final sample data sets；
Step 3: normalized
Data sample set obtained in step 2 is normalized, different data dimensions is eliminated；
Step 4: building regularization extreme learning machine
The data sample set of normalized in step 3 is randomly selected into 4/5ths data therein as training
Data set chooses remaining 1/5th data sample as test data set, then regularization extreme learning machine hidden layer section is arranged
Point number, hidden layer activation primitive and regularization coefficient, construct regularization extreme learning machine；
Step 5: the prediction of BOF Steelmaking Endpoint manganese content is carried out by regularization extreme learning machine
After bessemerizing beginning, BOF Steelmaking Endpoint manganese content is predicted by regularization extreme learning machine, is obtained
BOF Steelmaking Endpoint manganese content data.
Further improvement lies in that: detailed process in the step 1 are as follows: first to the medium and high carbon steel history number of converter smelting
According to being acquired, according to the influence factor of BOF Steelmaking Endpoint manganese content and terminal manganese content, in conjunction with metallurgical basic principle and fortune
Correlation analysis is carried out with Pearson (Pearson came) related coefficient, determines the input variable number of model, finding influences converter refining
The influence factor of steel terminal manganese content.
Further improvement lies in that: the input variable includes molten iron charge weight, steel scrap charge weight, molten iron temperature in converter
Degree, molten iron phosphorus content, molten iron manganese content, molten steel sulfur content, oxygen consumption, lime adding amount, light dolomite additional amount and change
Slag agent additional amount.
Further improvement lies in that: first the influence factor data of BOF Steelmaking Endpoint manganese content are adopted in the step 2
Collection, and the pretreatment of sample data is carried out to the factor for influencing BOF Steelmaking Endpoint manganese content, abnormal data is rejected, really
Fixed final sample data sets.
Further improvement lies in that: the method that the pretreatment of the data uses is by rejecting with data smoothing technique to different
Regular data is pre-processed.
Further improvement lies in that: the range that normalized data select in the step 3 is [- 1,1].
Further improvement lies in that: first the data sample set of normalized in step 3 is selected at random in the step 4
4/5ths data therein are taken as training dataset to train regularization extreme learning machine, choose remaining 1/5th number
The accuracy of this method, then the mean square error by comprehensively considering extreme learning machine prediction are verified as test data set according to sample
Difference and precision of prediction are arranged reasonable regularization extreme learning machine hidden layer node number, hidden layer activation primitive and regularization
Coefficient constructs regularization extreme learning machine.
Further improvement lies in that: the step 5 detailed process are as follows: collected and recorded in real time using process database system
The heat information of converter, obtained data sample is normalized, and normalized data range of choice is [- 1,1],
Then the sample data after normalized that process database system provides is input to foundation using industrial control computer
In the good BOF Steelmaking Endpoint manganese content prediction model based on regularization extreme learning machine, heat that scene is bessemerized into
The prediction of row manganese content.
Further improvement lies in that: industrial control computer for predicting that BOF Steelmaking Endpoint manganese contains in real time in the step 5
Amount.
Further improvement lies in that: process database is connected with industrial control computer in the step 5, the process
Then database provides data branch for acquiring in real time, recording convertor steelmaking process data for the operation of industrial control computer
Support.
The invention has the benefit that BOF Steelmaking Endpoint manganese content is predicted by regularization extreme learning machine,
The biasing for not needing the input weight and hidden layer of adjustment network in the training process, need to only be arranged the hiding node layer of network
Number, regularization coefficient and activation primitive can generate unique optimal solution, and the model training speed is fast, precision of prediction is high,
Adaptability is preferable, compared with based on the BOF Steelmaking Endpoints manganese content prediction model such as statistical method, expert system, BP neural network
Precision of prediction and arithmetic speed, which have, to be obviously improved, and then can carry out promptly and accurately pre- to BOF Steelmaking Endpoint manganese content
It surveys, while should measure that adaptability is good, the training time based on the BOF Steelmaking Endpoint manganese content prediction technique for then changing extreme learning machine
It is short, be not easy to fall into local optimum, and this method is without the largely parameters of setting neural networks and optimal net in the training process
The searching of network structural parameters, hence it is evident that improve the precision of prediction and arithmetic speed of BOF Steelmaking Endpoint manganese content.
Detailed description of the invention
Fig. 1 is the method for the present invention model construction and schematic diagram of calculation flow.
Fig. 2 is the method for the present invention Structure and Process schematic diagram.
Specific embodiment
In order to realize invention technological means, reach purpose and effect is easy to understand, below with reference to specific implementation
Mode, the present invention is further explained.
According to Fig. 1,2, the present embodiment proposes that the BOF Steelmaking Endpoint manganese content based on regularization extreme learning machine is pre-
Survey method, comprising the following steps:
Step 1: the selection of the input variable of regularization extreme learning machine
The medium and high carbon steel historical data of converter smelting is acquired first, according to the influence of BOF Steelmaking Endpoint manganese content
Factor and terminal manganese content carry out correlation analysis in conjunction with metallurgical basic principle and with Pearson (Pearson came) related coefficient,
The input variable number for determining model finds the influence factor for influencing BOF Steelmaking Endpoint manganese content, and input variable includes converter
In molten iron charge weight, steel scrap charge weight, molten iron temperature, molten iron phosphorus content, molten iron manganese content, molten steel sulfur content, oxygen consumption, stone
Grey additional amount, light dolomite additional amount and slagging agent additional amount；
Step 2: the pretreatment of sample data
First the influence factor data of BOF Steelmaking Endpoint manganese content are acquired, and contains to BOF Steelmaking Endpoint manganese is influenced
The factor of amount carries out the pretreatment of sample data, is pre-processed with data smoothing technique to abnormal data by rejecting, and determines
Final sample data sets.
Step 3: normalized
Data sample set obtained in step 2 is normalized, the range that normalized data select for
[- 1,1], eliminates different data dimensions；
Step 4: building regularization extreme learning machine
The data sample set of normalized in step 3 is first randomly selected into 4/5ths data therein as instruction
Practice data set to train regularization extreme learning machine, chooses remaining 1/5th data sample and verified as test data set
The accuracy of this method, then be arranged reasonably just by comprehensively considering mean square error and the precision of prediction that extreme learning machine is predicted
Then change extreme learning machine hidden layer node number, hidden layer activation primitive and regularization coefficient, constructs regularization extreme learning machine；
Step 5: the prediction of BOF Steelmaking Endpoint manganese content is carried out by regularization extreme learning machine
The heat information for being collected and recorded converter in real time using process database system, obtained data sample is returned
One change processing, normalized data range of choice are [- 1,1], then utilize industrial control computer by process database system
It is whole that sample data after the normalized provided of uniting is input to the established pneumatic steelmaking based on regularization extreme learning machine
In point manganese content prediction model, the prediction of manganese content is carried out to the heat that scene is bessemerized, industrial control computer is for real
When predict BOF Steelmaking Endpoint manganese content, process database is connected with industrial control computer, and the process database is used for
Acquisition in real time, record convertor steelmaking process data, then provide data supporting for the operation of industrial control computer.
It is measured using BOF Steelmaking Endpoint manganese content of the method for the present invention to 25 kinds of medium and high carbon steels, obtains table 1:
1 the method for the present invention of table measures test result
| Serial number | Steel grade | Manganese content predicted value % | Manganese content surveys reality % |
| 1 | Medium and high carbon steel | 0.19536 | 0.17000 |
| 2 | Medium and high carbon steel | 0.20693 | 0.22000 |
| 3 | Medium and high carbon steel | 0.16682 | 0.18000 |
| 4 | Medium and high carbon steel | 0.12879 | 0.12000 |
| 5 | Medium and high carbon steel | 0.15728 | 0.15000 |
| 6 | Medium and high carbon steel | 0.13375 | 0.14000 |
| 7 | Medium and high carbon steel | 0.18105 | 0.17000 |
| 8 | Medium and high carbon steel | 0.18094 | 0.16000 |
| 9 | Medium and high carbon steel | 0.16058 | 0.17000 |
| 10 | Medium and high carbon steel | 0.13197 | 0.16000 |
| 11 | Medium and high carbon steel | 0.1553 | 0.16000 |
| 12 | Medium and high carbon steel | 0.14776 | 0.17000 |
| 13 | Medium and high carbon steel | 0.16342 | 0.18000 |
| 14 | Medium and high carbon steel | 0.17809 | 0.19000 |
| 15 | Medium and high carbon steel | 0.1372 | 0.13000 |
| 16 | Medium and high carbon steel | 0.16234 | 0.17000 |
| 17 | Medium and high carbon steel | 0.16052 | 0.14000 |
| 18 | Medium and high carbon steel | 0.11757 | 0.10000 |
| 19 | Medium and high carbon steel | 0.15186 | 0.17000 |
| 20 | Medium and high carbon steel | 0.16249 | 0.18000 |
| 21 | Medium and high carbon steel | 0.16797 | 0.16000 |
| 22 | Medium and high carbon steel | 0.182 | 0.16000 |
| 23 | Medium and high carbon steel | 0.1755 | 0.18000 |
| 24 | Medium and high carbon steel | 0.17696 | 0.16000 |
| 25 | Medium and high carbon steel | 0.12964 | 0.14000 |
It can be concluded that, predict that hit rate of the error in ± 0.025% range is 88%, mean square error is by table 1
2.64×10-8。
BOF Steelmaking Endpoint manganese content is predicted by regularization extreme learning machine, does not need to adjust in the training process
The input weight of whole network and the biasing of hidden layer need to only be arranged the hidden layer node number of network, regularization coefficient and swash
Function living can generate unique optimal solution, and the model training speed is fast, precision of prediction is high, adaptability is preferable, relatively based on system
Count the precision of prediction and arithmetic speed of the BOF Steelmaking Endpoints manganese content prediction models such as method, expert system, BP neural network
Have and be obviously improved, and then prediction promptly and accurately can be carried out to BOF Steelmaking Endpoint manganese content, while should be based on then changing
The BOF Steelmaking Endpoint manganese content prediction technique measurement adaptability of extreme learning machine is good, the training time is short, is not easy to fall into part most
The figure of merit, and the searching of parameter and optimum network structure parameter of this method it is not necessary that neural network is largely arranged in the training process,
Significantly improve the precision of prediction and arithmetic speed of BOF Steelmaking Endpoint manganese content.
The basic principles, main features and advantages of the invention have been shown and described above.The technical staff of the industry should
Understand, the present invention is not limited to the above embodiments, and the above embodiments and description only describe originals of the invention
Reason, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes and improvements
It all fall within the protetion scope of the claimed invention.The claimed scope of the invention is by appended claims and its equivalent circle
It is fixed.
Claims (10)
1. the BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine, it is characterised in that: including following step
It is rapid:
Step 1: the selection of the input variable of regularization extreme learning machine
The medium and high carbon steel historical data of converter smelting is acquired, and determines influence BOF Steelmaking Endpoint manganese content influence factor
Collection；
Step 2: the pretreatment of sample data
The influence factor data of BOF Steelmaking Endpoint manganese content are acquired, then the sample data of acquisition is located in advance
Reason, determines final sample data sets；
Step 3: normalized
Data sample set obtained in step 2 is normalized, different data dimensions is eliminated；
Step 4: building regularization extreme learning machine
The data sample set of normalized in step 3 is randomly selected into 4/5ths data therein as training data
Collection chooses remaining 1/5th data sample as test data set, then regularization extreme learning machine hidden layer node is arranged
Number, hidden layer activation primitive and regularization coefficient construct regularization extreme learning machine；
Step 5: the prediction of BOF Steelmaking Endpoint manganese content is carried out by regularization extreme learning machine
After bessemerizing beginning, BOF Steelmaking Endpoint manganese content is predicted by regularization extreme learning machine, obtains converter
Make steel terminal manganese content data.
2. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 1 based on regularization extreme learning machine,
It is characterized in that: detailed process in the step 1 are as follows: the medium and high carbon steel historical data of converter smelting is acquired first, according to
The influence factor and terminal manganese content of BOF Steelmaking Endpoint manganese content in conjunction with metallurgical basic principle and use Pearson (Pierre
It is inferior) related coefficient progress correlation analysis, determine the input variable number of model, finding influences BOF Steelmaking Endpoint manganese content
Influence factor.
3. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 2 based on regularization extreme learning machine,
Be characterized in that: the input variable includes molten iron charge weight, steel scrap charge weight, molten iron temperature, molten iron phosphorus content, iron in converter
Water manganese content, molten steel sulfur content, oxygen consumption, lime adding amount, light dolomite additional amount and slagging agent additional amount.
4. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 1 based on regularization extreme learning machine,
It is characterized in that: first the influence factor data of BOF Steelmaking Endpoint manganese content being acquired in the step 2, and influence is turned
The factor that furnace makes steel terminal manganese content carries out the pretreatment of sample data, rejects to abnormal data, determines final sample
Data acquisition system.
5. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 4 based on regularization extreme learning machine,
Be characterized in that: the method that the pretreatment of the data uses for by reject and data smoothing technique abnormal data is located in advance
Reason.
6. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 1 based on regularization extreme learning machine,
Be characterized in that: the range that normalized data select in the step 3 is [- 1,1].
7. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 1 based on regularization extreme learning machine,
It is characterized in that: the data sample set of normalized in step 3 is first randomly selected therein five in the step 4/
Four data train regularization extreme learning machine as training dataset, choose remaining 1/5th data sample as test
Data set verifies the accuracy of this method, then the mean square error by comprehensively considering extreme learning machine prediction and precision of prediction come
Reasonable regularization extreme learning machine hidden layer node number, hidden layer activation primitive and regularization coefficient are set, canonical is constructed
Change extreme learning machine.
8. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 1 based on regularization extreme learning machine,
It is characterized in that: the step 5 detailed process are as follows: collect and record the heat information of converter in real time using process database system,
Obtained data sample is normalized, normalized data range of choice is [- 1,1], then utilizes industry control
Sample data after normalized that process database system provides is input to established based on regularization by computer processed
In the BOF Steelmaking Endpoint manganese content prediction model of extreme learning machine, the pre- of manganese content is carried out to the heat that scene is bessemerized
It surveys.
9. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 8 based on regularization extreme learning machine,
Be characterized in that: industrial control computer for predicting BOF Steelmaking Endpoint manganese content in real time in the step 5.
10. the BOF Steelmaking Endpoint manganese content prediction technique according to claim 8 based on regularization extreme learning machine,
Be characterized in that: process database is connected with industrial control computer in the step 5, and the process database is for real-time
Acquisition, record convertor steelmaking process data, then provide data supporting for the operation of industrial control computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811382179.6A CN109252009A (en) | 2018-11-20 | 2018-11-20 | BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811382179.6A CN109252009A (en) | 2018-11-20 | 2018-11-20 | BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109252009A true CN109252009A (en) | 2019-01-22 |
Family
ID=65043820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811382179.6A Pending CN109252009A (en) | 2018-11-20 | 2018-11-20 | BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109252009A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036081A (en) * | 2020-08-26 | 2020-12-04 | 北京科技大学 | Method for determining addition amount of silicon-manganese alloy in converter tapping based on yield prediction |
| CN113449466A (en) * | 2021-06-16 | 2021-09-28 | 淮阴工学院 | Solar radiation prediction method and system for optimizing RELM based on PCA and chaos GWO |
| CN113656930A (en) * | 2021-06-24 | 2021-11-16 | 华北理工大学 | Method for predicting phosphorus content of smelting end point by single slag method |
| CN114611844A (en) * | 2022-05-11 | 2022-06-10 | 北京科技大学 | Method and system for determining alloy addition amount in converter tapping process |
| US11621808B1 (en) * | 2019-10-16 | 2023-04-04 | Xilinx, Inc. | Machine learning based methodology for signal waveform, eye diagram, and bit error rate (BER) bathtub prediction |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102392095A (en) * | 2011-10-21 | 2012-03-28 | 湖南镭目科技有限公司 | Termination point prediction method and system for converter steelmaking |
| CN104537167A (en) * | 2014-12-23 | 2015-04-22 | 清华大学 | Interval type index forecasting method based on robust interval extreme learning machine |
| CN105925750A (en) * | 2016-05-13 | 2016-09-07 | 南阳理工学院 | Steelmaking end point prediction method based on neural networks |
| CN106096724A (en) * | 2016-06-21 | 2016-11-09 | 重庆科技学院 | Converter steelmaking process cost control method based on ELM neutral net and system |
| CN106951995A (en) * | 2017-03-22 | 2017-07-14 | 华东交通大学 | A kind of EHV transmission electric field extreme learning machine predicts multiple-objection optimization screen method |
| CN108256260A (en) * | 2018-02-05 | 2018-07-06 | 北京科技大学 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
-
2018
- 2018-11-20 CN CN201811382179.6A patent/CN109252009A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102392095A (en) * | 2011-10-21 | 2012-03-28 | 湖南镭目科技有限公司 | Termination point prediction method and system for converter steelmaking |
| CN104537167A (en) * | 2014-12-23 | 2015-04-22 | 清华大学 | Interval type index forecasting method based on robust interval extreme learning machine |
| CN105925750A (en) * | 2016-05-13 | 2016-09-07 | 南阳理工学院 | Steelmaking end point prediction method based on neural networks |
| CN106096724A (en) * | 2016-06-21 | 2016-11-09 | 重庆科技学院 | Converter steelmaking process cost control method based on ELM neutral net and system |
| CN106951995A (en) * | 2017-03-22 | 2017-07-14 | 华东交通大学 | A kind of EHV transmission electric field extreme learning machine predicts multiple-objection optimization screen method |
| CN108256260A (en) * | 2018-02-05 | 2018-07-06 | 北京科技大学 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
Non-Patent Citations (2)
| Title |
|---|
| 张小晨: ""基于极限学习机的转炉炼钢终点预测模型研究"", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
| 邓万宇 等: ""神经网络极速学习方法研究"", 《计算机学报》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11621808B1 (en) * | 2019-10-16 | 2023-04-04 | Xilinx, Inc. | Machine learning based methodology for signal waveform, eye diagram, and bit error rate (BER) bathtub prediction |
| CN112036081A (en) * | 2020-08-26 | 2020-12-04 | 北京科技大学 | Method for determining addition amount of silicon-manganese alloy in converter tapping based on yield prediction |
| CN112036081B (en) * | 2020-08-26 | 2021-06-01 | 北京科技大学 | Method for determining addition amount of silicon-manganese alloy in converter tapping based on yield prediction |
| CN113449466A (en) * | 2021-06-16 | 2021-09-28 | 淮阴工学院 | Solar radiation prediction method and system for optimizing RELM based on PCA and chaos GWO |
| CN113449466B (en) * | 2021-06-16 | 2023-12-01 | 淮阴工学院 | Solar radiation prediction method and system for optimizing RELM based on PCA and chaos GWO |
| CN113656930A (en) * | 2021-06-24 | 2021-11-16 | 华北理工大学 | Method for predicting phosphorus content of smelting end point by single slag method |
| CN113656930B (en) * | 2021-06-24 | 2023-11-17 | 华北理工大学 | Prediction method for smelting endpoint phosphorus content by adopting machine learning algorithm |
| CN114611844A (en) * | 2022-05-11 | 2022-06-10 | 北京科技大学 | Method and system for determining alloy addition amount in converter tapping process |
| US11900255B2 (en) | 2022-05-11 | 2024-02-13 | University Of Science And Technology Beijing | Multi-mode smelting method based on the classification system of molten iron |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109252009A (en) | BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine | |
| CN109447346B (en) | Converter oxygen consumption prediction method based on gray prediction and neural network combined model | |
| CN104630410A (en) | Real-time dynamic converter steelmaking quality prediction method based on data analysis | |
| CN114611844B (en) | Method and system for determining alloy addition amount in converter tapping process | |
| CN109063358B (en) | Novel blast furnace forward evaluation method | |
| CN109359723A (en) | Based on the converter terminal manganese content prediction technique for improving regularization extreme learning machine | |
| Farla et al. | The quality of energy intensity indicators for international comparison in the iron and steel industry | |
| CN112036081B (en) | Method for determining addition amount of silicon-manganese alloy in converter tapping based on yield prediction | |
| CN106198408B (en) | The method and device thereof of alloying component on-line checking and visualizing control in casting | |
| EP2935633B1 (en) | Method and device for predicting, controlling and/or regulating steelworks processes | |
| CN109935280A (en) | A kind of blast-melted quality prediction system and method based on integrated study | |
| CN113919206A (en) | Narrow composition control method for steelmaking alloying | |
| CN109754137B (en) | Method and apparatus for determining quality and/or grade of ferrous material product | |
| CN106834593A (en) | A kind of method that RH refining furnace decarbonization process data are determined with reference heats method | |
| CN106345823A (en) | On-line real-time mechanical property prediction method based on hot rolled steel coil production processes | |
| CN102373310B (en) | Method for guiding converter reblowing process operation | |
| CN104419799A (en) | Method for predicting carbon content of high-carbon steel on line during converter smelting | |
| CN104531936A (en) | On-line measure method for carbon content of molten steel in revolving furnace based on flame image characteristic | |
| CN115074480A (en) | Method and system for improving processing quality of steel-making production | |
| CN110954670A (en) | Method and system for continuously predicting phosphorus content of converter molten pool | |
| CN103276136A (en) | Converter-steelmaking molten steel phosphorus-determination method based on sublance system | |
| CN111126550B (en) | Neural network molten steel temperature forecasting method based on Monte Carlo method | |
| CN111518980A (en) | Correction method and system for converter end point carbon content prediction model | |
| CN109472090B (en) | Prediction method for minimum mixing time of steel ladle | |
| CN109234491A (en) | A kind of BOF Steelmaking Endpoint manganese content prediction technique based on extreme learning machine |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190122 |
|
| RJ01 | Rejection of invention patent application after publication |