CN106636616B - A kind of sinter yield prediction method based on bellows exhaust gas temperature - Google Patents
A kind of sinter yield prediction method based on bellows exhaust gas temperature Download PDFInfo
- Publication number
- CN106636616B CN106636616B CN201611187766.0A CN201611187766A CN106636616B CN 106636616 B CN106636616 B CN 106636616B CN 201611187766 A CN201611187766 A CN 201611187766A CN 106636616 B CN106636616 B CN 106636616B
- Authority
- CN
- China
- Prior art keywords
- sinter
- yield
- sintering
- warm status
- bellows
- 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.)
- Active
Links
Classifications
-
- C—CHEMISTRY; METALLURGY
- C22—METALLURGY; FERROUS OR NON-FERROUS ALLOYS; TREATMENT OF ALLOYS OR NON-FERROUS METALS
- C22B—PRODUCTION AND REFINING OF METALS; PRETREATMENT OF RAW MATERIALS
- C22B1/00—Preliminary treatment of ores or scrap
- C22B1/14—Agglomerating; Briquetting; Binding; Granulating
- C22B1/16—Sintering; Agglomerating
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Materials Engineering (AREA)
- Mechanical Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Manufacture And Refinement Of Metals (AREA)
Abstract
The sinter yield prediction method based on bellows exhaust gas temperature that the invention discloses a kind of, includes the following steps：Determine the Warm status parameter for the yield rate for influencing sinter；Establish the historical production data sample database of sintering parameter；Calculate the yield rate of sinter；It is carried out curve fitting to bellows exhaust gas temperature data using polynomial fitting method, extremum method is asked by differential, obtains the numerical value of Warm status parameter；Based on the numerical value of Warm status parameter, sinter yield prediction model is established；The bellows exhaust gas temperature data of mine to be predicted are carried out curve fitting to obtain the numerical value of the Warm status parameter of mine to be predicted；The numerical value of the Warm status parameter of mine to be predicted is inputted into sinter yield prediction model, output variable is the yield rate of mine to be predicted.The present invention is capable of the yield rate of Accurate Prediction sinter, adjusts technological parameter in real time for sintering process with the yield rate and energy-saving consumption-reducing that improve sinter and provides important evidence.
Description
Technical field
Energy-saving field is produced the present invention relates to steel sintering process more particularly to a kind of based on bellows exhaust gas temperature
Sinter yield prediction method.
Background technology
Steel and iron industry is one of pillar industry in national economy, and the development of steel and iron industry will also determine the hair of Chinese national economy
Exhibition.Steel is widely used in the industry such as national defence, traffic, building, machine-building, automobile, has very in the national economic development
Important strategic position.Iron ore powder sintering is one of the important link in steel manufacture process, is to ensure that blast furnace obtains high-quality burning
The key point for tying mine, a certain amount of fuel and solvent are added into iron-containing ore raw materials, is tiled after mixing granulation
Sintering ignition is carried out on sintering machine, makes mixture that a series of physical and chemical reaction occur under the high temperature conditions, generation
High-quality is the primary raw material of blast fumance containing iron agglomerate.In steel production, the quality of sinter and yield effect steel
Quality and yield restrict the growth of business economic productivity effect.The prediction technique of sinter yield rate is conducive to look-ahead
The yield of sinter, to realize adjustment raw material parameter, device parameter and sintering operation parameter in advance, for improving sinter
Quality and yield play an important role.
Steel production process is more, technological process is long, and sintering process includes mainly：Sintered material, mixing granulation, segregation cloth
The process procedures such as material, ignition, the broken, cooling screening of hot mine.Currently, the sintering machine used in sintering process is typically all
Strand exhaust sintering machine is made of material-feeding mechanism, host, igniter, large flue, Water-seal zipper conveyor etc..The technique of sintering process
Flow is shown in attached drawing 1.
In sintering production process, the hot environment (Warm status) that fuel combustion provides in mixture is to influence sinter quality
With the most important procedure parameter of yield, it is to predict that the quality of sinter and yield are crucial to be accurately identified to it.In sintering process
Height, the length of hot environment retention time and the mixture of mixture local environment temperature complete the position residing for sintering process
It sets, can all influence the yield rate and quality of sinter.The lamination of sinter bed is shown in attached drawing 2.
Currently, worker mainly carries out prediction sinter finished product by sintering end point temperature and position in sintering production process
Rate adjusts fuel amount of allocating and sintering machine speed according to testing result, but this detection mode often burns in mixture
It could be carried out after the completion of knot, there is certain hysteresis quality, while only according to the temperature information at sintering end point moment, it can not be complete
React to face Warm status of the mixture in entire sintering process；And this prediction is mainly by controlling sintering end point temperature
With at position in a certain range, the case where quality and yield to judge sinter, there is no directly to sinter at
Product rate is predicted.Therefore, directly predict that the yield rate of sinter has weight to blast furnace ironmaking by sintering process Warm status
The meaning wanted.
Invention content
In view of this, the embodiment provides it is a kind of the yield rate of sintering process sinter can be carried out it is accurate pre-
The sinter yield prediction method based on bellows exhaust gas temperature surveyed.
The embodiment of the present invention provides a kind of sinter yield prediction method based on bellows exhaust gas temperature, including following
Step：
(1) the Warm status parameter for the yield rate for influencing sinter, the Warm status are determined according to the sintering process of sinter
Parameter includes bellows high-temperature temperature, high temperature hold time, sintering end point temperature and sintering end point position；
(2) historical production data of the sintering parameter to influencing sintering process carries out at zero-phase filtering and sequential registration
Reason, and sampling processing is carried out to the historical production data, establish historical production data sample database, the sintering parameter packet
It includes bellows exhaust gas temperature, machine speed, little Cheng Kuang, return mine and great achievement mine；
(3) yield rate of sinter is calculated using the historical production data sample database；
(4) use polynomial fitting method to the bellows exhaust gas temperature data in the historical production data sample database into
Row curve matching obtains a fitting function, seeks extreme value by carrying out differential to the fitting function, obtains Warm status parameter
Numerical value；The numerical value for obtaining Warm status parameter includes the following steps：
(4.1) bellows exhaust gas temperature data sample is chosen from the historical production data sample database, if bellows number
Mesh is M, with (Xi,T(Xi)) indicate a sample data, i=1,2 ... M, XiWith a distance from indicating i-th of bellows at igniting, T
(Xi) indicate to be X with a distance from ignitingiBellows exhaust gas temperature value；
(4.2) polynomial fitting method is used, to one group of sample data (X in bellows exhaust gas temperature data samplei,T
(Xi)) fitting of a polynomial is carried out, obtaining fitting function is
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0,
a8、a7、a6、a5、a4、a3、a2、a1And a0The coefficient being respectively fitted；
(4.3) fitting function in step (4.2) is subjected to a derivation and obtains the first order derivative multinomial of fitting function,
And solve XiValue, the X that will be solvediValue substitutes into the maximum of T that fitting function can be found out in fitting functionmax, TmaxFor wind
The peak of case exhaust gas temperature curve, as sintering end point temperature, XiFor sintering end point position；
If the sintering end point temperature of matched curve is more than 300 DEG C, and the corresponding sintering of sintering end point temperature obtained is eventually
Point is setting between penultimate bellows and third last bellows, then fitting function is reasonable, so that it is determined that fitting function
With reasonability；
(4.4) the first order derivative multinomial of fitting function in step (4.3) is subjected to derivation, obtains the secondary of fitting function
Derivative multinomial, and solve XiValue；The X that will be solvediValue, which substitutes into fitting function, can find out bellows high-temperature temperature value Tp,
By T (X)=TpIt substitutes into fitting function and finds out X1And X2, wherein X2>X1；
(4.5) according to sintering mechanism, the X solved in step (4.4) is utilized1And X2Value, using formula △ X=X2-
X1, its difference △ X are obtained, high temperature hold time can be obtained using △ X, the calculation formula of the high temperature hold time is as follows：
In formula：T indicates high temperature hold time,Indicate that pallet average speed, the pallet average speed are
Given value；
(5) numerical value of the Warm status parameter obtained using step (4) is as input variable, the sintering obtained with step (3)
The yield rate of mine is computed repeatedly and is verified as output variable, and sinter yield rate is established according to support vector regression algorithm
Prediction model；It is described sinter yield prediction model is established according to support vector regression algorithm to include the following steps：
(5.1) set the sample data set of the yield rate composition of Warm status parameter and sinter as
{(xi,yi), i=1,2 ... n }, xiFor input parameter, yiIt is exported for corresponding target, i.e. the yield rate of sinter；
(5.2) input parameter is mapped to higher dimensional space using Nonlinear Mapping, input parameter is carried out in higher dimensional space
Linear regression, and solve the optimization problem of linear regression problem：
In formula, ε is loss function parameter, and C is penalty factor, K (xi·xj) it is gaussian kernel function,αiIt is weight coefficient；
(5.3) optimization problem in (5.2) is solved, obtaining sinter yield prediction model is：
In formula：K(xi, x)=exp (- | | xi-x||2/2σ2), σ is kernel function width, and b is amount of bias, and the calculating of b values is public
Formula is：
(6) it carries out curve fitting to the bellows exhaust gas temperature data of mine to be predicted using polynomial fitting method and passes through differential
Extremum method is asked to obtain the numerical value of the Warm status parameter of mine to be predicted；
(7) numerical value of the Warm status parameter for the mine to be predicted for obtaining step (6) as input variable input sinter at
The output variable of product rate prediction model, the sinter yield prediction model is the yield rate of mine to be predicted.
Further, in the step (1), Warm status parameter is obtained by analyzing the mechanism of sintering process.
Further, in the step (2), the selected sampling period carries out sampling processing to historical production data, described to adopt
The sample period is the period of waves of great achievement mine, and the period of waves of the great achievement mine is 45min.
Further, after the yield rate of sinter refers to sintering process, finished product sinter accounts for the proportion of sinter cake, institute
The calculation formula for stating the yield rate of sinter is as follows：
In formula：ρ indicates the yield rate (%) of sinter, QDIndicate the great achievement mineral products amount (Kg/h) of sintering, QXIndicate sintering
It is small at mineral products amount (Kg/h), QFIndicate the quantity of return mines (Kg/h) of sintering；It is the great achievement mineral products amount, small at mineral products amount and quantity of return mines
Data are obtained from historical production data sample database.
Further, the detailed process for establishing sinter yield prediction model is：Randomly select multigroup be sintered
The yield data and Warm status supplemental characteristic of mine, by a part of finished product in multigroup yield data and Warm status supplemental characteristic
Rate data and Warm status supplemental characteristic are as training data, using a part of Warm status supplemental characteristic as input variable, with institute
It is that output variable is computed repeatedly to state a part of yield data, establishes sinter yield prediction model；By multigroup finished product
Remainder yield data and Warm status supplemental characteristic in rate data and Warm status supplemental characteristic is as test data, with institute
It is input variable to state remainder Warm status supplemental characteristic, inputs sinter yield prediction model, the sinter yield rate
The output variable of prediction model be yield rate predicted value, by the predicted value of the remainder yield data and yield rate into
Row verification.
Compared with prior art, the invention has the advantages that：
(1) present invention determines the Warm status parameter for the yield rate for influencing sinter by the Analysis on Mechanism of sintering process, and
Using bellows exhaust gas temperature data, the numerical value of Warm status parameter has been obtained, it can be achieved that directly predicting the yield rate of sinter, to burn
Knot process adjusts technological parameter and provides important evidence to improve sinter yield rate and energy-saving consumption-reducing in real time；
(2) the present invention is based on Warm status parameters, and sinter yield prediction model is established according to support vector regression algorithm,
Can directly predict sinter yield rate, be effectively ensured prediction model it is accurate with it is reasonable；
(3) the present invention is based on the historical production datas of sintering process, carry out the emulation experiment of prediction model, can be in reality
Extensive use in production process.
Description of the drawings
Fig. 1 is the sintering process process flow chart of strand exhaust sintering machine.
Fig. 2 is the schematic diagram of the sinter bed lamination of strand exhaust sintering machine.
Fig. 3 is the flow chart of one embodiment of the invention.
Fig. 4 is the bellows exhaust gas temperature matched curve figure of one embodiment of the invention.
Fig. 5 is difference △ X schematic diagrames on the bellows exhaust gas temperature curve of one embodiment of the invention.
Fig. 6 is the comparison diagram of the predicted value and actual yield data of the yield rate of one embodiment of the invention.
Fig. 7 is the error amount of the predicted value and actual yield data of the yield rate of one embodiment of the invention.
Specific implementation mode
The invention will be further described with reference to the accompanying drawings and examples.
Using the present invention provides a kind of sinter yield prediction method based on bellows exhaust gas temperature, Fig. 3 is please referred to,
The present embodiment includes the following steps：
(1) the Warm status parameter for the yield rate for influencing sinter is determined by analyzing the mechanism of the sintering process of sinter,
Sintering process includes solid phase reaction and liquid phase reactor, and liquid phase reactor can generate calcium ferrite liquid phase, and calcium ferrite liquid phase is sinter
The major influence factors of yield rate, and the generation of calcium ferrite liquid phase is mainly influenced by sinter bed Warm status, is sintered simultaneously
The variation of bed of material Warm status can be reflected by the variation of bellows exhaust gas temperature curve, main for bellows exhaust gas temperature curve
Characteristic parameter is bellows high-temperature temperature, high temperature hold time, sintering end point temperature and sintering end point position, therefore influences sinter
The Warm status parameter of yield rate include bellows high-temperature temperature, high temperature hold time, sintering end point temperature and sintering end point position.
(2) historical production data of the sintering parameter to influencing sintering process carries out at zero-phase filtering and sequential registration
Reason, and selected great achievement mine period of waves 45min as the sampling period to historical production data progress sampling processing, establish history
Creation data sample database；Sintering parameter includes bellows exhaust gas temperature, machine speed, little Cheng Kuang, returns mine and great achievement mine；
In one embodiment, the detailed process for establishing historical production data sample database is as follows：Collect sintering machine one month
Historical production data, acquire each bellows exhaust gas temperature, machine speed, great achievement mine, small produce number at mine and the history returned mine
According to since there are uncertain factor, there are more hairs in historical production data in historical production data gatherer process
Thorn, to need to collected each box temperature in sintering process, machine speed, great achievement mine, small at mine and that returns mine go through
History creation data carries out zero-phase filtering processing；Then to each box temperature, machine speed, great achievement mine, small at mine and return mine
Historical production data carry out sequential registration process, to ensure that sintering process supplemental characteristic is consistent in sequential；Using big
At mine period of waves 45min as the sampling period, to the historical production data being registrated by zero-phase filtering processing and sequential
Sampling processing is carried out, to establish historical production data sample database.
(3) historical production data sample database is utilized to calculate the yield rate of sinter；The yield rate of sinter refers to
After sintering process, finished product sinter accounts for the proportion of sinter cake, and the calculation formula of the yield rate of sinter is as follows：
In formula：ρ indicates the yield rate (%) of sinter, QDIndicate the great achievement mineral products amount (Kg/h) of sintering, QXIndicate sintering
It is small at mineral products amount (Kg/h), QFIndicate the quantity of return mines (Kg/h) of sintering；Great achievement mineral products amount, the small data at mineral products amount and quantity of return mines
It is obtained from historical production data sample database.
(4) use polynomial fitting method to the bellows exhaust gas temperature data march in historical production data sample database
Line is fitted to obtain a fitting function, seeks extreme value by carrying out differential to fitting function, obtains the numerical value of Warm status parameter；
The numerical value for obtaining Warm status parameter specifically includes following steps：
(4.1) bellows exhaust gas temperature data sample is chosen from historical production data sample database, if bellows number is
M, with (Xi,T(Xi)) indicate a sample data, i=1,2 ... M, XiWith a distance from indicating i-th of bellows at igniting, T (Xi) table
Show with a distance from igniting to be XiBellows exhaust gas temperature value；
(4.2) polynomial fitting method is used, to one group of sample data (X in bellows exhaust gas temperature data samplei,T
(Xi)) fitting of a polynomial is carried out, obtaining fitting function is
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0,
a8、a7、a6、a5、a4、a3、a2、a1And a0The coefficient being respectively fitted；
(4.3) fitting function in step (4.2) is subjected to a derivation and obtains the first order derivative multinomial of fitting function,
And solve XiValue, the X that will be solvediValue substitutes into the maximum of T that fitting function can be found out in fitting functionmax, TmaxFor wind
The peak of case exhaust gas temperature curve, as sintering end point temperature, XiFor sintering end point position；
If the sintering end point temperature of matched curve is more than 300 DEG C, and the corresponding sintering of sintering end point temperature obtained is eventually
Point is setting between penultimate bellows and third last bellows, then fitting function is reasonable, so that it is determined that fitting function
With reasonability；
(4.4) the first order derivative multinomial of fitting function in step (4.3) is subjected to derivation, obtains the secondary of fitting function
Derivative multinomial, and solve XiValue；The X that will be solvediValue, which substitutes into fitting function, can find out bellows high-temperature temperature value Tp,
By T (X)=TpIt substitutes into fitting function and finds out X1And X2, wherein X2>X1；
(4.5) according to sintering mechanism, the X solved in step (4.4) is utilized1And X2Value, using formula △ X=X2-
X1, its difference △ X are obtained, high temperature hold time can be obtained using △ X, the calculation formula of high temperature hold time is as follows：
In formula：T indicates high temperature hold time,Indicate pallet average speed, pallet average speed is known
Value.
Using above-mentioned steps, with reference to Fig. 2, a steel mill 360m2Sintering machine shares 24 bellows, between each bellows away from
From difference, according to the actual conditions of this sintering machine, 1 be able to detect that for scene#、2#、3#、 5#、7#、9#、11#、13#、
15#、17#、18#、19#、20#、21#、22#、23#、24#The exhaust gas temperature value of bellows, correspond to respectively on pallet from igniting at
Distance be 1.5m, 4.5m, 7.5m, 14m, 22m, 30m, 38m, 46m, 54m, 62m, 66m, 70m, 74m, 78m, 82m,
85.5m、88.5m；
One group of sample data (X is chosen in the bellows exhaust gas temperature value detectedi,T(Xi)), i=1,2 ... 17, it is specific
Value be (1.5,89.09154431), (4.5,58.20210398) ... (88.5,294.3742171), totally 17 groups, using multinomial
Fitting process, it is 8 times to choose polynomial number, can solve fitting function T (Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4
+a3Xi 3+a2Xi 2+a1Xi 1+a0Coefficient value a8、a7、a6、 a5、a4、a3、a2、a1And a0, the coefficient value of fitting function is by four houses
Five enter after numerical value it is as shown in the table, bellows exhaust gas temperature matched curve figure is shown in Fig. 4.
The coefficient value of fitting function after rounding up
| a8 | a7 | a6 | a5 | a4 | a3 | a2 | a1 | a0 |
| -2.69e-11 | 9.18e-9 | -1.28e-6 | 9.19e-5 | -0.004 | 0.071 | -0.691 | 3.18 | -181.6 |
The coefficient value of the fitting function solved is updated to fitting function
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0In, fitting function is carried out primary
Derivation obtains the first order derivative multinomial of fitting function, solves following equation and X can be obtainediValue；
dT(Xi)/dXi=d (a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0)/dXi=8a8Xi 7+
7a7Xi 6+6a6Xi 5+5a5Xi 4+4a4Xi 3+3a3Xi 2+2a2Xi 1+a1=0
The X that will be solvediValue is updated to fitting function
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0In, that is, solve one group of sample number
According in XiT in ∈ [0m, 90m]max, TmaxFor the peak of bellows exhaust gas temperature curve.Work as X by can be calculatediWhen=83,
TmaxBe maximized is 356.6533.It is found that sintering end point temperature is 356.6533 DEG C, sintering end point position is 83m；
Sintering end point temperature is more than 300 DEG C at this time and sintering end point position is located at penultimate bellows and third last
Between bellows, illustrate that the fitting function is reasonable；In general, the maximum temperature of bellows exhaust gas temperature curve 300 DEG C with
On.
The coefficient value of the fitting function solved is substituted into fitting function
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0In, the primary of fitting function is led
Number multinomial carries out derivation, obtains the second derivative multinomial of fitting function, and solve the X of following equationiValue；
56a8Xi 6+42a7Xi 5+30a6Xi 4+20a5Xi 3+12a4Xi 2+6a3Xi+2a2=0
The X that will be solvediValue substitutes into fitting function
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0In, bellows high-temperature temperature value can be obtained
Tp=259.4902, then by T (X)=Tp=259.4902 substitute into fitting function
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0In acquire X1And X2, X can be obtained1=
70.800 X2=89.8207, using formula △ X=X2-X1, obtain its difference △ X=89.8207-70.800=19.0207；
Difference △ X schematic diagrames are shown in Fig. 5 on bellows exhaust gas temperature curve；
Since high temperature hold time is equal to difference △ X divided by pallet average speed, so being solved according to above-mentioned
△ X and known pallet average speed, can find out high temperature hold time t, be expressed as：
(5) numerical value of the Warm status parameter obtained using step (4) is as input variable, the sintering obtained with step (3)
The yield rate of mine is computed repeatedly and is verified as output variable, and sinter yield rate is established according to support vector regression algorithm
Prediction model；
According to support vector regression algorithm establish sinter yield prediction model the specific steps are：
(5.1) set the sample data set of the yield rate composition of Warm status parameter and sinter as
{(xi,yi), i=1,2 ... n }, xiFor input parameter, yiIt is exported for corresponding target, i.e. the yield rate of sinter；
(5.2) input parameter is mapped to higher dimensional space using Nonlinear Mapping, input parameter is carried out in higher dimensional space
Linear regression, and solve the optimization problem of linear regression problem：
In formula, ε is loss function parameter, and C is penalty factor, K (xi·xj) it is gaussian kernel function,αiIt is weight coefficient；
(5.3) optimization problem in (5.2) is solved, obtaining sinter yield prediction model is：
In formula：K(xi, x)=exp (- | | xi-x||2/2σ2), σ is kernel function width, and b is amount of bias, and the calculating of b values is public
Formula is：
(6) it carries out curve fitting to the bellows exhaust gas temperature data of mine to be predicted using polynomial fitting method and passes through differential
Extremum method is asked to obtain the numerical value of the Warm status parameter of mine to be predicted；
(7) sinter yield prediction model is inputted using the numerical value of the Warm status parameter of mine to be predicted as input variable,
The output variable of sinter yield prediction model is the yield rate of mine to be predicted.
In one embodiment, 200 groups of yield data of sinter and Warm status supplemental characteristics are randomly selected, with 170 groups
Yield data and Warm status supplemental characteristic are as training data, using Warm status supplemental characteristic as input variable, with yield rate number
It is computed repeatedly according to for output variable, establishes sinter yield prediction model；
It is that input becomes with Warm status supplemental characteristic using 30 groups of yield datas and Warm status supplemental characteristic as test data
Amount inputs sinter yield prediction model, and the output variable of sinter yield prediction model is the predicted value of yield rate, will
The predicted value of yield data and yield rate is verified, the comparison diagram and error amount point of predicted value and actual yield data
Do not see Fig. 6 and Fig. 7, as shown in Figure 7, the relative error of the prediction result of the yield rate of sinter [- 0.06%, 0.08%] it
Interior, therefore, the sinter yield prediction model of foundation has feasibility.
This method may be implemented directly to predict the yield rate of sinter, and predictablity rate is high, is adjusted in real time for sintering process
Technological parameter provides important evidence to improve sinter yield rate and energy-saving consumption-reducing.
In the absence of conflict, the feature in embodiment and embodiment herein-above set forth can be combined with each other.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Claims (5)
1. a kind of sinter yield prediction method based on bellows exhaust gas temperature, it is characterised in that：Include the following steps：
(1) the Warm status parameter for the yield rate for influencing sinter, the Warm status parameter are determined according to the sintering process of sinter
Including bellows high-temperature temperature, high temperature hold time, sintering end point temperature and sintering end point position；
(2) historical production data of the sintering parameter to influencing sintering process carries out zero-phase filtering and sequential registration process, and
Sampling processing is carried out to the historical production data, establishes historical production data sample database, the sintering parameter includes wind
Case exhaust gas temperature, little Cheng Kuang, is returned mine and great achievement mine at machine speed；
(3) yield rate of sinter is calculated using the historical production data sample database；
(4) use polynomial fitting method to the bellows exhaust gas temperature data march in the historical production data sample database
Line is fitted to obtain a fitting function, seeks extreme value by carrying out differential to the fitting function, obtains the numerical value of Warm status parameter；
The numerical value for obtaining Warm status parameter includes the following steps：
(4.1) bellows exhaust gas temperature data sample is chosen from the historical production data sample database, if bellows number is
M, with (Xi,T(Xi)) indicate a sample data, i=1,2 ... M, XiWith a distance from indicating i-th of bellows at igniting, T (Xi) table
Show with a distance from igniting to be XiBellows exhaust gas temperature value；
(4.2) polynomial fitting method is used, to one group of sample data (X in bellows exhaust gas temperature data samplei,T(Xi)) carry out
Fitting of a polynomial, obtaining fitting function is
T(Xi)=a8Xi 8+a7Xi 7+a6Xi 6+a5Xi 5+a4Xi 4+a3Xi 3+a2Xi 2+a1Xi 1+a0,
a8、a7、a6、a5、a4、a3、a2、a1And a0The coefficient being respectively fitted；
(4.3) fitting function in step (4.2) is subjected to a derivation and obtains the first order derivative multinomial of fitting function, and asked
Solve XiValue, the X that will be solvediValue substitutes into the maximum of T that fitting function can be found out in fitting functionmax, TmaxIt is useless for bellows
The peak of gas temperature curve, as sintering end point temperature, XiFor sintering end point position；
If the sintering end point temperature of matched curve is more than 300 DEG C, and the corresponding sintering end point position of sintering end point temperature obtained
Setting between penultimate bellows and third last bellows, then fitting function is reasonable, so that it is determined that fitting function has
Reasonability；
(4.4) the first order derivative multinomial of fitting function in step (4.3) is subjected to derivation, obtains the second derivative of fitting function
Multinomial, and solve XiValue；The X that will be solvediValue, which substitutes into fitting function, can find out bellows high-temperature temperature value Tp, by T
(X)=TpIt substitutes into fitting function and finds out X1And X2, wherein X2>X1；
(4.5) according to sintering mechanism, the X solved in step (4.4) is utilized1And X2Value, using formula △ X=X2-X1, obtain
Its difference △ X can obtain high temperature hold time using △ X, and the calculation formula of the high temperature hold time is as follows：
In formula：T indicates high temperature hold time,Indicate pallet average speed, the pallet average speed is known
Value；
(5) numerical value of the Warm status parameter obtained using step (4) is as input variable, the sinter obtained with step (3)
Yield rate is computed repeatedly and is verified as output variable, and sinter yield prediction is established according to support vector regression algorithm
Model；It is described sinter yield prediction model is established according to support vector regression algorithm to include the following steps：
(5.1) sample data set of the yield rate composition of Warm status parameter and sinter is set as { (xi,yi), i=1,2 ... n }, xi
For input parameter, yiIt is exported for corresponding target, i.e. the yield rate of sinter；
(5.2) input parameter is mapped to higher dimensional space using Nonlinear Mapping, input parameter is carried out in higher dimensional space linear
It returns, and solves the optimization problem of linear regression problem：
In formula, ε is loss function parameter, and C is penalty factor, K (xi·xj) it is gaussian kernel function,αiIt is weight coefficient；
(5.3) optimization problem in (5.2) is solved, obtaining sinter yield prediction model is：
In formula：K(xi, x)=exp (- | | xi-x||2/2σ2), σ is kernel function width, and b is amount of bias, and the calculation formula of b values is：
(6) it carries out curve fitting to the bellows exhaust gas temperature data of mine to be predicted using polynomial fitting method and pole is asked by differential
Value method obtains the numerical value of the Warm status parameter of mine to be predicted；
(7) numerical value of the Warm status parameter for the mine to be predicted for obtaining step (6) inputs sinter yield rate as input variable
The output variable of prediction model, the sinter yield prediction model is the yield rate of mine to be predicted.
2. the sinter yield prediction method based on bellows exhaust gas temperature as described in claim 1, which is characterized in that described
In step (1), Warm status parameter is obtained by analyzing the mechanism of sintering process.
3. the sinter yield prediction method based on bellows exhaust gas temperature as described in claim 1, which is characterized in that described
In step (2), the sampling period is selected to historical production data progress sampling processing, the sampling period is the fluctuation week of great achievement mine
The period of waves of phase, the great achievement mine are 45min.
4. the sinter yield prediction method based on bellows exhaust gas temperature as described in claim 1, which is characterized in that sintering
After the yield rate of mine refers to sintering process, finished product sinter accounts for the proportion of sinter cake, the meter of the yield rate of the sinter
It is as follows to calculate formula：
In formula：ρ indicates the yield rate (%) of sinter, QDIndicate the great achievement mineral products amount (Kg/h) of sintering, QXIndicate sintering it is small at
Mineral products amount (Kg/h), QFIndicate the quantity of return mines (Kg/h) of sintering；The great achievement mineral products amount, the small data at mineral products amount and quantity of return mines
It is obtained from historical production data sample database.
5. the sinter yield prediction method based on bellows exhaust gas temperature as described in claim 1, which is characterized in that described
The detailed process for establishing sinter yield prediction model is：Randomly select the yield data and Warm status of multigroup sinter
Supplemental characteristic, by a part of yield data and Warm status supplemental characteristic in multigroup yield data and Warm status supplemental characteristic
It is defeated with a part of yield data using a part of Warm status supplemental characteristic as input variable as training data
Go out variable to be computed repeatedly, establishes sinter yield prediction model；By multigroup yield data and Warm status supplemental characteristic
In remainder yield data and Warm status supplemental characteristic as test data, with the remainder Warm status parameter number
According to for input variable, inputting sinter yield prediction model, the output variable of the sinter yield prediction model be at
The predicted value of product rate verifies the predicted value of the remainder yield data and yield rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611187766.0A CN106636616B (en) | 2016-12-20 | 2016-12-20 | A kind of sinter yield prediction method based on bellows exhaust gas temperature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611187766.0A CN106636616B (en) | 2016-12-20 | 2016-12-20 | A kind of sinter yield prediction method based on bellows exhaust gas temperature |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106636616A CN106636616A (en) | 2017-05-10 |
| CN106636616B true CN106636616B (en) | 2018-09-04 |
Family
ID=58833576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611187766.0A Active CN106636616B (en) | 2016-12-20 | 2016-12-20 | A kind of sinter yield prediction method based on bellows exhaust gas temperature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106636616B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107236862B (en) * | 2017-07-06 | 2018-08-10 | 重庆大学 | A kind of sinter bed temperature predicting method based on logarithm normal distribution function |
| CN109654897B (en) * | 2018-11-30 | 2020-03-31 | 中国地质大学（武汉） | Intelligent sintering end point control method for improving carbon efficiency |
| CN111105151B (en) * | 2019-12-10 | 2022-05-20 | 珠海格力电器股份有限公司 | Air conditioner material prediction method, system and storage medium |
| CN111553048B (en) * | 2020-03-23 | 2023-09-22 | 中国地质大学（武汉） | Method for predicting operation performance of sintering process based on Gaussian process regression |
| CN112255364B (en) * | 2020-10-20 | 2022-07-01 | 唐山学院 | Soft measurement method for real-time quantitative determination of sintering end point state |
| CN113254738B (en) * | 2021-04-27 | 2022-01-04 | 佛山众陶联供应链服务有限公司 | Self-adaptive prediction method and device of firing curve and computer storage medium |
| CN115090855B (en) * | 2022-06-30 | 2023-07-04 | 中国联合网络通信集团有限公司 | Control method, device and equipment for part machining |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60204841A (en) * | 1984-03-29 | 1985-10-16 | Sumitomo Metal Ind Ltd | Production of sintered ore |
| JPH0288724A (en) * | 1988-09-27 | 1990-03-28 | Kawasaki Steel Corp | Method for operating sintering machine |
| CN101598934B (en) * | 2009-07-14 | 2011-01-05 | 北京首钢自动化信息技术有限公司 | Method for indirectly controlling sintering end point |
| CN101975514B (en) * | 2010-11-16 | 2012-09-26 | 吕斌 | Through burning control method for sintering production |
| CN105039685B (en) * | 2015-08-03 | 2017-03-22 | 中南大学 | Method for soft measurement of iron ore sintering process state |
| CN105624394B (en) * | 2016-01-13 | 2017-11-07 | 中国地质大学（武汉） | A kind of sinter bed Warm status recognition methods based on bellows EGT |
| CN106155137A (en) * | 2016-08-29 | 2016-11-23 | 甘肃酒钢集团宏兴钢铁股份有限公司 | A kind of sintering end point temperature automatic control method |
-
2016
- 2016-12-20 CN CN201611187766.0A patent/CN106636616B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106636616A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106636616B (en) | A kind of sinter yield prediction method based on bellows exhaust gas temperature | |
| CN106802977B (en) | Method for predicting performance index of sinter and evaluating comprehensive quality | |
| JP6503055B2 (en) | Method of detecting distribution of blast furnace gas flow | |
| CN106777684B (en) | Method for establishing comprehensive coke ratio prediction model and predicting comprehensive coke ratio | |
| CN106521059B (en) | Blast furnace charge level ore coke ratio is measured with phased-array radar to control the method for blast furnace air flow method | |
| CN110070217A (en) | A kind of Forcasting Sinter Quality method of Kernel-based methods parameter | |
| CN105468799B (en) | Forecast the emulation mode of high-temp waste gas cycle sintering process heat state parameter | |
| CN106755972A (en) | A kind of method that sintering process comprehensive coke ratio is predicted based on Data Dimensionality Reduction method | |
| JP6911808B2 (en) | Control device for sinter manufacturing equipment, sinter manufacturing equipment and sinter manufacturing method | |
| US20110170114A1 (en) | Method of controlling a transformation process of charge material to a product | |
| CN105624394B (en) | A kind of sinter bed Warm status recognition methods based on bellows EGT | |
| Assis et al. | Artificial neural network-based committee machine for predicting fuel rate and sulfur contents of a coke blast furnace. | |
| CN114842918B (en) | Automatic water adding method for sintering mixture based on machine learning | |
| Saveliev et al. | Analysis and synthesis of factors determining the sintering speed of sinter charge | |
| JP2017008363A (en) | Method for estimating layer thickness distribution in blast furnace, method for operating blast furnace, and device for estimating layer thickness distribution in blast furnace | |
| Ryabchikov et al. | Simulation of the combined effect of production factors on metallurgical sinter mechanical strength | |
| CN106834662B (en) | A kind of CO/CO based on multi-state sintering process2Ratio prediction technique | |
| Ye et al. | Tumble strength prediction for sintering: data-driven modeling and scheme design | |
| Mohanan et al. | Prediction and optimization of internal return fines generation in iron ore sintering using machine learning | |
| CN107066659A (en) | A kind of method that limit of utilization learning machine predicts cement decomposing furnace temperature | |
| Muller et al. | A finite difference model of the iron ore sinter process | |
| Ryabchikov | Metallurgical agglomerate quality management with the account of its impact on the blast-furnace process efficiency | |
| CN102305805B (en) | Method for detecting moisture distribution at material layer in chain grate machine in pelletizing production process | |
| Saiz et al. | Non-linear state estimator for the on-line control of a sinter plant | |
| CN114216349B (en) | Sintering end point forecasting method based on coding and decoding network |
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 |