CN106777652A - A kind of method for predicting blast furnace permeability - Google Patents
A kind of method for predicting blast furnace permeability Download PDFInfo
- Publication number
- CN106777652A CN106777652A CN201611131609.8A CN201611131609A CN106777652A CN 106777652 A CN106777652 A CN 106777652A CN 201611131609 A CN201611131609 A CN 201611131609A CN 106777652 A CN106777652 A CN 106777652A
- Authority
- CN
- China
- Prior art keywords
- parameter
- data
- blast furnace
- factor
- 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.)
- Granted
Links
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
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21B—MANUFACTURE OF IRON OR STEEL
- C21B5/00—Making pig-iron in the blast furnace
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The present invention provides a kind of method for predicting blast furnace permeability, including:Gather the historical data of operation of blast furnace database;Analysis of history data are simultaneously pre-processed, and selection historical data obtains meeting the real data of production requirement;The factor of influence of blast furnace permeability in current slot is obtained, and factor of influence is carried out into weight sequencing by the contribution of importance;Corresponding data set is set up according to gas permeability factor of influence weight sequencing result;The factor of influence of data set is classified according to gas permeability parameter, the center of factor of influence in each classification is calculated;Based on black-box model modeling, several gas permeabilities prediction submodel is set up;The raw material and fuel quality parameter or operational control parameter after adjustment are input into corresponding gas permeability according to its corresponding categorical data as needed predict submodel;According to operation of blast furnace database gathered data frequency, dynamic is updated using latest data to model parameter.The present invention can dynamically update gas permeability model, improve precision of prediction.
Description
Technical field
The present invention relates to aided control technology field in blast furnace ironmaking, more particularly to a kind of side for predicting blast furnace permeability
Method.
Background technology
Blast furnace permeability represents under certain condition, the ability that gas stream in the stove passes through the bed of material, and it directly determines blast furnace coal
Air flow method whether rationally so that finally influence blast fumance whether stable smooth operation.Therefore in blast fumance, the conjunction of gas permeability
Anticipation and effectively control are managed as one of most crucial operation link, always interested in ironmaking worker.
The change of blast furnace permeability is relevant with the factors in production, such as crude fuel, air-supply, cloth etc. all can be to saturating
Gas produces influence.But since for a long time, blast furnace operating person is the passive change for deacclimatizing blast furnace permeability, by each
Empirical method is planted, solves the problems, such as that gas permeability deteriorates, this often makes conditions of blast furnace fluctuation occur.In the last few years, with blast furnace
The raising of automaticity and the lifting of managerial skills, blast furnace operating person have gradually paid attention to the anticipation problem in advance of gas permeability.But
Research in terms of current gas permeability prediction also has that the model such as set up only possesses off-line calculation, or influence
Factor chooses only consideration part and is preset parameter, it is difficult to adapt to industrial applications etc., therefore in actual production, operator couple
The control of gas permeability still mostly by rule of thumb, this direct motion to blast furnace has a negative impact.
Therefore, the traditional passive reply pattern of urgent need change, then integrated information from every side, judge that blast furnace is breathed freely in advance
The variation tendency of property, so that take measures to be prevented in advance,
The content of the invention
The shortcoming of prior art in view of the above, it is an object of the invention to provide a kind of side for predicting blast furnace permeability
Method, for solving in existing blast fumance administrative skill, operator relies on micro-judgment and the passively change of reply gas permeability,
So as to easily cause the problem of working of a furnace fluctuation.
Step one, gathers the historical data of operation of blast furnace database, and the historical data is used comprising current slot
Raw material and fuel quality parameter, operational control parameter and data corresponding to gas permeability parameter;
Step 2, analysis of history data are simultaneously pre-processed, and select the reality that the historical data obtains meeting production requirement
Border data;
Step 3, obtains the factor of influence of blast furnace permeability in current slot, and the factor of influence is pressed into importance
Contribution carry out weight sequencing;
Step 4, according to gas permeability factor of influence weight sequencing result, the larger some factors of selection weighing factor with it is saturating
Gas parameter sets up one-to-one data set;
Step 5, the factor of influence of data set is classified according to gas permeability parameter, is classified successively according to data label,
The factor of influence and gas permeability data under some classifications are formed, the center of factor of influence in each classification is calculated;
Step 6, based on black-box model modeling, under some classification, sets up several gas permeabilities prediction respectively
Model;
Step 7, when blast furnace permeability Long-term change trend is predicted, by the raw material and fuel quality parameter after adjustment or operation control
Parameter processed, is input into corresponding gas permeability according to its corresponding categorical data and predicts submodel;
Step 8, according to the frequency of operation of blast furnace database gathered data, mould is predicted using newest data to gas permeability
The parameter of type is updated.
In order to achieve the above objects and other related objects, the present invention provides a kind of method for predicting blast furnace permeability, including:
As described above, the method for dynamic evaluation conditions of blast furnace direct motion of the invention, has the advantages that:
The present invention is taking into full account that blast furnace uses crude fuel by using available data analysis mining and modeling technique
On the basis of condition and operating parameter, rational factor of influence is selected with the weight of each gas permeability influence factor, and according to influence
The cluster result of the factor sets up sub- forecast model, and when adjustment blast furnace raw material or operation is needed, operator only need to be by after adjustment
Parameter input model, corresponding sub- forecast model is automatically selected by model according to data characteristics, you can obtain gas permeability change feelings
Condition, realizes the prediction to blast furnace permeability, solves blast furnace operating personnel and blast furnace permeability is judged by rule of thumb and is brought
Problem, can judge that gas permeability change direction provides support for blast furnace operating person, so as to judge whether operation adjustment rationally carries
For foundation.Meanwhile, the present invention can realize the dynamic renewal of gas permeability prediction, i.e., with the refreshing of blast furnace real time data, breathe freely
Property forecast model also simultaneously dynamic update, can so be obtained according to the change of the working of a furnace in time influence gas permeability factor sort
And classification results, and then Optimized model precision of prediction, so as to avoid that big fluctuation occurs due to data maintenance or the working of a furnace
When, predict the outcome inaccurate problem, it is easy to accomplish industrialized application.
Brief description of the drawings
Fig. 1 is shown as the flow chart of blast furnace permeability Forecasting Methodology of the invention;
Fig. 2 is shown as the schematic diagram of factor of influence data set classification of the invention;
Fig. 3 is shown as the schematic diagram that blast furnace permeability forecast model of the invention is used.
Component label instructions:
S101~S108:Step one is to step 8
Specific embodiment
Embodiments of the present invention are illustrated below by way of specific instantiation, those skilled in the art can be by this specification
Disclosed content understands other advantages of the invention and effect easily.The present invention can also be by specific realities different in addition
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that, in the case where not conflicting, following examples and implementation
Feature in example can be mutually combined.
It should be noted that the diagram provided in following examples only illustrates basic structure of the invention in a schematic way
Think, component count, shape and size when only display is with relevant component in the present invention rather than according to actual implementation in schema then
Draw, it is actual when the implementing kenel of each component, quantity and ratio can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
Fig. 1 is referred to, the present invention provides a kind of method flow diagram of blast furnace permeability prediction, including:
In step S101, the historical data of operation of blast furnace database is gathered, the historical data includes current slot
Used raw material and fuel quality parameter, operational control parameter and data corresponding to gas permeability parameter;
Specifically, the raw material and fuel quality parameter, the coke primary quality measure used by blast fumance and sintering deposit,
The primary quality measure of pellet, lump ore.Wherein, coke primary quality measure include granularmetric composition, Industrial Analysis, M40, M10,
CSR, CRI etc., sintering deposit, pellet, the primary quality measure of lump ore include that chemical composition, granularmetric composition, basicity, physics are strong
Degree, reproducibility etc.;
The operational control parameter, is the four big systems and the related major parameter that taps a blast furnace involved by blast fumance, including
Material parameter processed, blowing system parameter, slagging regime parameter, thermal system and parameter of tapping a blast furnace etc..
The selection of gas permeability parameter is crushing, is calculated by below equation:
Wherein:S --- crushing, Pamin/Nm3;Δ P --- total head is poor, kpa;VBG--- gas flowrate in bosh, Nm3/min
The historical data, the data of the last period historical time, the point on the basis of current time for it, taking time span is
The measurement of past H hours calculates data, and with M minutes moving average, as one group of data, (each parameter had 60*H/M numbers
According to), wherein, 1≤H≤240,1≤M≤10;
In the present embodiment, join by the current institute's raw material and fuel quality parameter of blast furnace, operational control parameter and gas permeability
Number corresponding data collection, can provide data basis for the analysis of follow-up rationally accurate data and modeling.
In step s 102, analysis of history data and pre-processed, selecting that the historical data obtains meeting production will
The real data asked;
Specifically, it is described that data are screened and screened, it is the ginseng for collecting in the daily production process of blast furnace
Number scope determines rational parameter threshold, and abnormal data is then judged as more than this threshold value, is rejected, it is to avoid influence gas permeability
The correctness for predicting the outcome;
In the present embodiment, by using available data analytical technology, abnormal historical data is screened and filters out, it is reachable
More suit the purpose of produce reality situation to making blast furnace permeability predict the outcome.
In step s 103, the factor of influence of blast furnace permeability in current slot is obtained, and the factor of influence is pressed
The contribution of importance carries out weight sequencing;
Specifically, the factor of influence of the blast furnace permeability, is to adopt in the blast furnace production process being previously mentioned in step S101
Raw material and fuel quality parameter, the operational control parameter for collecting;
The factor of influence weight sequencing, is using available data digging technology, by analyzing gas permeability and factor of influence
Between relation, calculate weighted index, factor of influence is ranked up successively from big to small according to weighted index;Weighted index
Span 0~1, it is K to take the number of raw material and fuel quality parameter and operational control parameter, and the weighted index of each parameter is W1、
W2、…、WK, wherein, 0≤Wi≤ 1, i=1,2 ..., K and
In the present embodiment, by the weight sequencing to each gas permeability factor of influence, can reach as blast furnace permeability is predicted
The purpose of precision parameter is provided.
In step S104, according to gas permeability factor of influence weight sequencing result, selection weighing factor it is larger it is some because
Son starts against one-to-one data set together with gas permeability parameter;
Specifically, the selection larger some factors of weighing factor, according in step S101 the selected time then
In section, according to the change of each Factor Weight sum in step S103, it is determined that raw material and fuel quality parameter, operation needed for follow-up modeling
Control parameter, i.e., carry out importance screening to the various parameters listed by step S101, and screening principle is:
It is K to take the number of raw material and fuel quality parameter and operational control parameter, and the weighted index of each parameter is according to from big to small
It is W1、W2、…、WK, corresponding parameter name is A1、A2、…、AK, wherein, 0≤Wi≤ 1, i=1,2 ..., K, as ∑ Wi≥0.8
When, select WiCorresponding parameter A before1、A2、…、AiAs the follow-up parameter for using.
The data set, is the parameter A obtained according to weight sequencing1、A2、…、Ai, each parameter is according in step S101
It is described, by one group by data set current and that phase of history time data point is constituted before, i.e., the point on the basis of current time,
It is the measurement of H hours in the past or calculating data to take time span, and with M minutes moving average, as one group of data, (each parameter had N
=60*H/M data), wherein, 1≤H≤240,1≤M≤10, the concrete form of data set is as follows:
Wherein AiNRepresent parameter AiThe record value at n-th moment, SNRepresent the crushing measured value of correspondence n-hour.
In the present embodiment, the larger parameter of influence gas permeability is screened by weight sequencing, is can reach as subsequent prediction side
Method reduces dimension, improves the purpose of the real-time and accuracy for calculating.
In step S105, the factor of influence of data set is classified according to gas permeability parameter, according to data label according to
Subseries, forms the factor of influence and gas permeability data under some classifications, calculates the center of factor of influence in each classification;
Specifically, factor of influence classification, be by the data of the N group factors of influence in the data set in step S104,
I.e.Self attributes according to each group of data are classified, class number is respectively 1,2 ... ... n, its
Middle n≤5, the data set under each class is illustrated as shown in Figure 2;
The data label, corresponding moment point when being record data entry;
Described each classification factor of influence center, is, according to sorted each factor of influence parameter values, to calculate this class
In each factor of influence average value, computational methods are exemplified below formula:
WhereinPresentation class for n classification in, parameter A1The center of all data, i.e., the average value of all data;A1i
Represent the parameter A in the n-th class1In the value at certain moment, j is represented in the n-th class comprising parameter A1Quantity.
In the present embodiment, by determining the classification of each factor of influence, lower factor of influence of all categories and gas permeability are formed
Data set, and the center of each classification factor of influence is calculated, can reach as the foundation of follow-up gas permeability forecast model is provided more
The accurately purpose of data.
In step s 106, based on black-box model modeling, under some classification, several gas permeabilities are set up respectively
Prediction submodel;
Specifically, several gas permeabilities prediction submodel, is according under each classification obtained in step S105
Factor of influence and gas permeability data set, set up black-box model, and each factor of influence is then as mode input parameter, gas permeability parameter
Output parameter, gas permeability prediction submodel quantity need to be consistent with classification number in step S105;
In the present embodiment, by set up it is different classes of under ventilative sub-model, reach can make gas permeability predict knot
The purpose of the different raw material and fuel quality parameter of really more targeted adaptation and operational control parameter type.
In step s 107, when blast furnace permeability Long-term change trend is predicted, by the raw material and fuel quality parameter after adjustment or
Operational control parameter, is input into corresponding gas permeability according to its corresponding categorical data and predicts submodel;
Specifically, it is described to sort out with reference to data center, it is to join the raw material and fuel quality parameter after adjustment or operational control
It is carried out traversal contrast by array into one group of new data with the factor of influence center of each classification of calculating in step S105,
Using available data digging technology, its data characteristics which kind of is best suited is calculated, so as to be sorted out into that class.
The corresponding gas permeability prediction submodel of selection, according to categorization results, selects the gas permeability under its classification to predict
Submodel, one group of new data is constituted as |input paramete using the raw material and fuel quality parameter after adjustment or operational control parameter,
Then model can export the permeability value of prediction, and specifically used method is as shown in Figure 3.
In the present embodiment, the raw material and fuel quality parameter or operational control parameter after to adjustment are sorted out, point
Prediction submodel that Shi Yong be under respective classes, can reach the purpose for more accurately predicting the outcome.
In step S108, according to the frequency of operation of blast furnace database gathered data, using newest data to gas permeability
The parameter of forecast model is updated.
Specifically, the model is dynamically updated using latest data, is that model can be according to the renewal of blast furnace data collection frequently
Rate, the most early stage history modeling data of corresponding duration is covered with latest data, so that model can realize mobilism again
Set up.
In the present embodiment, by taking into full account the renewal frequency that blast furnace data is gathered, dynamic is predicted blast furnace permeability
Model is rebuild, and can reach the purpose for ensureing prediction effect correctness, or model maintenance provides good use bar
Part.
In sum, the present invention is taking into full account blast furnace institute by using available data analysis mining and modeling technique
On the basis of using crude fuel condition and operating parameter, rational factor of influence is selected with the weight of each gas permeability influence factor,
And sub- forecast model is set up according to the cluster result of factor of influence, when adjustment blast furnace raw material or operation is needed, operator only needs
By the parameter input model after adjustment, corresponding sub- forecast model is automatically selected according to data characteristics by model, you can obtain
Gas situation of change, realizes the prediction to blast furnace permeability, and solve blast furnace operating personnel is carried out to blast furnace permeability by rule of thumb
The problem judged and bring, can judge that gas permeability change direction provides support for blast furnace operating person, so as to judge operation adjustment
Whether foundation is rationally provided.Meanwhile, the present invention can realize the dynamic renewal of gas permeability prediction, i.e., with blast furnace real time data
Refresh, also dynamic updates gas permeability forecast model simultaneously, can so be obtained influenceing gas permeability according to the change of the working of a furnace in time
Factor sequence and classification results, and then Optimized model precision of prediction, so as to avoid sending out due to data maintenance or the working of a furnace
When giving birth to big fluctuation, predict the outcome inaccurate problem, it is easy to accomplish industrialized application.So, the present invention effectively overcomes
Various shortcoming of the prior art and have high industrial utilization.
The above-described embodiments merely illustrate the principles and effects of the present invention, not for the limitation present invention.It is any ripe
The personage for knowing this technology all can carry out modifications and changes under without prejudice to spirit and scope of the invention to above-described embodiment.Cause
This, those of ordinary skill in the art is complete with institute under technological thought without departing from disclosed spirit such as
Into all equivalent modifications or change, should be covered by claim of the invention.
Claims (9)
1. it is a kind of predict blast furnace permeability method, it is characterised in that including:
Step one, gathers the historical data of operation of blast furnace database, and the historical data uses former combustion comprising current slot
Material mass parameter, operational control parameter and data corresponding to gas permeability parameter;
Step 2, analysis of history data are simultaneously pre-processed, and select the actual number that the historical data obtains meeting production requirement
According to;
Step 3, obtains the factor of influence of blast furnace permeability in current slot, and the factor of influence is pressed the tribute of importance
Offering size carries out weight sequencing;
Step 4, according to gas permeability factor of influence weight sequencing result, selection weighing factor larger some factors and gas permeability
Parameter sets up one-to-one data set;
Step 5, the factor of influence of data set is classified according to gas permeability parameter, is classified successively according to data label, is formed
Factor of influence and gas permeability data under some classifications, calculate the center of factor of influence in each classification;
Step 6, based on black-box model modeling, under some classification, sets up several gas permeabilities prediction submodule respectively
Type;
Step 7, when blast furnace permeability Long-term change trend is predicted, the raw material and fuel quality parameter after adjustment or operational control is joined
Number, is input into corresponding gas permeability according to its corresponding categorical data and predicts submodel;
Step 8, according to the frequency of operation of blast furnace database gathered data, using newest data to gas permeability forecast model
Parameter is updated.
2. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the step one is specifically included:
The raw material and fuel quality parameter, the coke quality index used by blast fumance and sintering deposit, pellet, the matter of lump ore
Figureofmerit;
The operational control parameter, is four big systems and the parameter of tapping a blast furnace involved by blast fumance, and it includes material parameter processed, air-supply
System parameter, slagging regime parameter, thermal system and parameter of tapping a blast furnace;
The selection of gas permeability parameter is crushing, is calculated by below equation:
Wherein:S is expressed as crushing, and its unit is Pamin/Nm3;It is poor that Δ P is expressed as total head, and its unit is kpa;VBGIt is expressed as
Gas flowrate in bosh, its unit is Nm3/min;
The historical data of the current slot, the point on the basis of current time, take time span be in the past H hours measurement or
Data are calculated, is one group of data (each parameter there are N=60*H/M data) with M minutes moving average, wherein, 1≤H≤
240,1≤M≤10.
3. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the specific bag of the step 2
Include:
The historical data is screened and screened according to blast furnace default parameter threshold, judge collection furnace parameters high whether
In the range of default parameter threshold, if it was not then for abnormal data is rejected.
4. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the step 3 is specifically included:
Obtain the factor of influence of blast furnace permeability in current slot, the factor of influence is to collect in blast furnace production process
Raw material and fuel quality parameter, operational control parameter;
Using the relation between Analysis on Data Mining gas permeability and factor of influence, weighted index is calculated, referred to according to weight
Number is ranked up to factor of influence successively from big to small;Wherein, weighted index span 0~1, take raw material and fuel quality parameter and
The number of operational control parameter is K, and the weighted index of each parameter is W1、W2、…、WK, wherein, 0≤Wi≤ 1, i=1,2 ..., K
And
5. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the step 4 is specifically included:
According to the change of each Factor Weight sum in current slot, it is determined that the required raw material and fuel quality parameter of follow-up modeling,
Operational control parameter;
The number for obtaining raw material and fuel quality parameter and operational control parameter is K, and the weighted index of each parameter is according to being from big to small
W1、W2、…、WK, corresponding parameter name is A1、A2、…、AK, wherein, 0≤Wi≤ 1, i=1,2 ..., K, as ∑ WiWhen >=0.8,
Selection WiCorresponding parameter A before1、A2、…、AiAs the follow-up parameter for using.
According to the parameter A that weight sequencing is obtained1、A2、…、Ai, each parameter have one group by current slot group of data points into
Data set, the concrete form of data set is as follows:
Wherein AiNRepresent parameter AiThe record value at n-th moment, SNRepresent the crushing measured value of correspondence n-hour.
6. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the step 5 is specifically included:
The data of N groups factor of influence in the data set, the self attributes according to each group of data are classified, class number point
Wei 1,2 ... ... n, wherein n≤5;
The data label, corresponding moment point when being record data entry;
According to sorted each factor of influence parameter values, the average value of each classification factor of influence is calculated using equation below,
WhereinPresentation class for n classification in, parameter A1The center of all data, i.e., the average value of all data;A1iRepresent
The parameter A in the n-th class1In the value at certain moment, j is represented in the n-th class comprising parameter A1Quantity.
7. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the step 6 is specifically included:
Using black-box model according to the factor of influence under each classification and gas permeability data set, correspond to each classification and build one thoroughly
Gas predicts submodel, wherein, used as mode input parameter, gas permeability parameter is then output parameter to factor of influence.
8. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the step 7 is specifically included:
Raw material and fuel quality parameter after adjustment or operational control parameter are constituted into one group of new data, every group of new data and each class
Other factor of influence center carries out traversal contrast, calculates its data characteristics which kind of is best suited and is sorted out;
The gas permeability under its classification is selected to predict submodel according to categorization results, by the raw material and fuel quality parameter after adjustment or behaviour
Make control parameter as |input paramete, the then permeability value that the output of gas permeability forecast model is predicted.
9. it is according to claim 1 prediction blast furnace permeability method, it is characterised in that the step 8 is specifically included:
The frequency of latest data is gathered according to operation of blast furnace database, the most early stage history of corresponding duration is covered using latest data
The data of modeling, dynamic updates the latest data of gas permeability forecast model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611131609.8A CN106777652B (en) | 2016-12-09 | 2016-12-09 | method for predicting air permeability of blast furnace |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611131609.8A CN106777652B (en) | 2016-12-09 | 2016-12-09 | method for predicting air permeability of blast furnace |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106777652A true CN106777652A (en) | 2017-05-31 |
CN106777652B CN106777652B (en) | 2019-12-17 |
Family
ID=58879449
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611131609.8A Active CN106777652B (en) | 2016-12-09 | 2016-12-09 | method for predicting air permeability of blast furnace |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106777652B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109685289A (en) * | 2019-01-21 | 2019-04-26 | 重庆电子工程职业学院 | Conditions of blast furnace direct motion prediction technique, apparatus and system |
CN109871978A (en) * | 2018-12-28 | 2019-06-11 | 广州兴森快捷电路科技有限公司 | A kind of PCB order qualification rate prediction technique, device and readable storage medium storing program for executing |
CN111680932A (en) * | 2020-06-23 | 2020-09-18 | 武汉钢铁有限公司 | Method and device for acquiring cause of abnormal furnace condition of blast furnace |
CN114264585A (en) * | 2020-09-16 | 2022-04-01 | 宝山钢铁股份有限公司 | Method for simulating and measuring air permeability of carbon-iron composite furnace charge for production |
CN116340795A (en) * | 2023-05-29 | 2023-06-27 | 山东一然环保科技有限公司 | Operation data processing method for pure oxygen combustion heating furnace |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SU1052540A1 (en) * | 1981-05-28 | 1983-11-07 | Завод-ВТУЗ при Карагандинском металлургическом комбинате | Method for continuously measuring gas permeability of charge in blast furnace |
KR20140002212A (en) * | 2012-06-28 | 2014-01-08 | 현대제철 주식회사 | Judgment method of gas distribution of blast furnace |
JP2015140455A (en) * | 2014-01-28 | 2015-08-03 | Jfeスチール株式会社 | Blast furnace permeability prediction device and blast furnace permeability prediction method |
CN104899463A (en) * | 2015-06-18 | 2015-09-09 | 中南大学 | Blast furnace molten iron silicon content four-classification trend prediction model establishing method and application |
CN106022377A (en) * | 2016-05-20 | 2016-10-12 | 中南大学 | Online prediction method for iron ore sintering bed permeability states |
-
2016
- 2016-12-09 CN CN201611131609.8A patent/CN106777652B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SU1052540A1 (en) * | 1981-05-28 | 1983-11-07 | Завод-ВТУЗ при Карагандинском металлургическом комбинате | Method for continuously measuring gas permeability of charge in blast furnace |
KR20140002212A (en) * | 2012-06-28 | 2014-01-08 | 현대제철 주식회사 | Judgment method of gas distribution of blast furnace |
JP2015140455A (en) * | 2014-01-28 | 2015-08-03 | Jfeスチール株式会社 | Blast furnace permeability prediction device and blast furnace permeability prediction method |
CN104899463A (en) * | 2015-06-18 | 2015-09-09 | 中南大学 | Blast furnace molten iron silicon content four-classification trend prediction model establishing method and application |
CN106022377A (en) * | 2016-05-20 | 2016-10-12 | 中南大学 | Online prediction method for iron ore sintering bed permeability states |
Non-Patent Citations (1)
Title |
---|
梁栋 等: "《高炉透气性指数智能预测模型》", 《重庆大学学报(自然科学版)》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109871978A (en) * | 2018-12-28 | 2019-06-11 | 广州兴森快捷电路科技有限公司 | A kind of PCB order qualification rate prediction technique, device and readable storage medium storing program for executing |
CN109685289A (en) * | 2019-01-21 | 2019-04-26 | 重庆电子工程职业学院 | Conditions of blast furnace direct motion prediction technique, apparatus and system |
CN109685289B (en) * | 2019-01-21 | 2020-11-10 | 重庆电子工程职业学院 | Method, device and system for forward prediction of blast furnace conditions |
CN111680932A (en) * | 2020-06-23 | 2020-09-18 | 武汉钢铁有限公司 | Method and device for acquiring cause of abnormal furnace condition of blast furnace |
CN111680932B (en) * | 2020-06-23 | 2023-04-07 | 武汉钢铁有限公司 | Method and device for acquiring cause of abnormal furnace condition of blast furnace |
CN114264585A (en) * | 2020-09-16 | 2022-04-01 | 宝山钢铁股份有限公司 | Method for simulating and measuring air permeability of carbon-iron composite furnace charge for production |
CN114264585B (en) * | 2020-09-16 | 2023-11-14 | 宝山钢铁股份有限公司 | Method for simulating and measuring air permeability of carbon-iron composite furnace burden for production |
CN116340795A (en) * | 2023-05-29 | 2023-06-27 | 山东一然环保科技有限公司 | Operation data processing method for pure oxygen combustion heating furnace |
Also Published As
Publication number | Publication date |
---|---|
CN106777652B (en) | 2019-12-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106777652A (en) | A kind of method for predicting blast furnace permeability | |
Coakley et al. | A review of methods to match building energy simulation models to measured data | |
Xu et al. | Discrete time–cost–environment trade-off problem for large-scale construction systems with multiple modes under fuzzy uncertainty and its application to Jinping-II Hydroelectric Project | |
CN106909705A (en) | A kind of blast-melted quality prediction method and its system | |
CN107045788A (en) | Traffic Forecasting Methodology and device | |
CN106345823B (en) | The method of online real-time estimate mechanical performance based on coils of hot-rolled steel production procedure | |
CN109726503A (en) | Missing data complementing method and device | |
CN109636616B (en) | Method for realizing project group progress master control management | |
CN107944708A (en) | Borrow or lend money the model discrimination method, apparatus and storage medium of risk control | |
CN107977758A (en) | A kind of rainfall intensity forecasting procedure and relevant apparatus | |
Chen et al. | A BIM-integrated fuzzy multi-criteria decision making model for selecting low-carbon building measures | |
CN104517162A (en) | On-line hardness forecasting method of continuous annealing product by means of integrated learning | |
CN109408848A (en) | A kind of distributed attribution method considering Runoff Evolution temporal-spatial heterogeneity | |
CN114358427B (en) | Method for predicting final recoverable reserves of shale gas well | |
CN106980874B (en) | A kind of multi-time Scales dimension data fusion method towards distribution big data | |
CN105023061B (en) | Iron and steel enterprise's gas balance based on prediction model result dispatches system and method | |
CN107491840A (en) | The prediction of flowing wearing character and lifetime estimation method based on ELM neural network models | |
Zhang et al. | Development of an innovation diffusion model for renewable energy deployment | |
CN107092751A (en) | Variable weight model combination forecasting method based on Bootstrap | |
CN104751254A (en) | Line loss rate prediction method based on non-isometric weighted grey model and fuzzy clustering sorting | |
CN117469603B (en) | Multi-water-plant water supply system pressure optimal control method based on big data learning | |
CN102156405B (en) | Sintered ore chemical component prediction and intelligent control system under small sample poor information | |
CN105224801A (en) | A kind of multiple-factor reservoir reservoir inflow short-time forecast evaluation method | |
CN103279030A (en) | Bayesian framework-based dynamic soft measurement modeling method and device | |
CN102103501B (en) | Method for forecasting software development cost and execution time aiming at reworking |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |