CN107038307B - The Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach - Google Patents
The Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach Download PDFInfo
- Publication number
- CN107038307B CN107038307B CN201710250996.5A CN201710250996A CN107038307B CN 107038307 B CN107038307 B CN 107038307B CN 201710250996 A CN201710250996 A CN 201710250996A CN 107038307 B CN107038307 B CN 107038307B
- Authority
- CN
- China
- Prior art keywords
- warm area
- temperature
- model
- data
- indicate
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Control Of Temperature (AREA)
Abstract
The invention discloses a kind of Roller Conveying Kiln for Temperature for combining mechanism with data to predict integrated modelling approach, by establishing mechanism model from the angle of temperature change and energy to the factor analysis for influencing temperature change；Then in view of roller kilns sintering is a sufficiently complex process, entire sintering process can not be described by a single mechanism model, and mechanism model is that there are model errors by simplifying, data model is established to predict model error, it is exported with this to make up mechanism, i.e., establishes the error prediction model of the nonlinear time-varying process returned based on local weighted core principle component using error as training sample；Last mechanism model is combined with data model establishes Roller Conveying Kiln for Temperature prediction integrated model.The state change of process can be preferably tracked using the model that the present invention obtains, and good directive function is provided for Roller Conveying Kiln for Temperature control, to improve production quality and qualification rate.
Description
Fields
The invention belongs to roller kilns field of smelting, and in particular to Roller Conveying Kiln for Temperature predicts integrated modelling approach
Background technique
Lithium battery has the characteristics that operating voltage is high, specific energy is big, has extended cycle life, is light-weight, is low in the pollution of the environment, full generation
Boundary's various fields have a wide range of applications, such as mobile phone, electric vehicle engineering, Medical Instruments power supply etc..Wherein there is generation
The battery of table is using roller kilns as production platform, and cobalt acid lithium is the lithium battery of positive electrode.Produce anode material of lithium battery
Sintering equipment roller kilns are a kind of light body continuous industry kilns, have the spies such as low energy consumption, firing period is short, furnace temperature decision is good
Point, in addition it is also the distributed system of a heat flow field, is divided into three area Ge great of warming-up section, constant temperature zone and cooling section, Mei Ge great
Area is divided into several cells again.Wherein, Roller Conveying Kiln for Temperature is a most key parameter in system operation, too high or too low for temperature
Adverse effect will be brought to product quality, maintaining temperature stabilization is to guarantee the necessary condition of product quality.
Currently, being limited by work condition environment, the operation informations such as oxygen flow distribution, burden distribution inside roller kilns and process
Parameter is difficult to obtain, and partial differential equation have the problems such as solving complexity, known conditions requires harshness, single from temperature field, stream
It angularly sets out field, it is difficult to establish accurate partial differential equation mathematical model.Roller Conveying Kiln for Temperature variation tendency in order to obtain, it is close
Researcher generallys use one order time delay system as the model of system according to the characteristics of roller kilns and makees approximate model to temperature over year,
But the result that this simplified model estimates temperature has large error with actual temperature value, so establishing one can solve
It is convenient, and can preferably estimate that the mechanism model of Roller Conveying Kiln for Temperature is current problem to be resolved.However due to sintering process
Complexity, mechanism model can not embody the factor of had an impact temperature, and obtained result and actual temperature, which can inevitably exist, to be missed
Difference, therefore, more accurate Temperature estimate value, the error generated in advance to model carry out prediction and need to solve in order to obtain
A big problem.
Summary of the invention
The purpose of the present invention is to provide a kind of Roller Conveying Kiln for Temperature combined based on mechanism with data to predict integrated moulding
Method establishes mechanism model from the angle of temperature change and energy variation, then utilize mechanism model output and reality
The difference of temperature establishes data model as training sample, predicts error, finally by mechanism model and data model
Output summation is exported as final temperature, is used to solve the problems, such as with this of the existing technology.
A kind of Roller Conveying Kiln for Temperature prediction integrated modelling approach combined based on mechanism with data, is included the following steps:
1) data processing step: roller kilns process operation data are arranged, created data are stored in
In library；
2) modelling by mechanism based on temperature Yu energy variation relationship: temperature of charge can not be measured directly, and thermocouple is measured
Temperature is regarded as entirely going up warm area or lower warm area temperature, and roller kilns sintering is the process of slow time-varying, and sampling point power is considered as Δ t
Power in=5min, it is assumed that each warm area pressure is constant；
Secondly, the factor for influencing temperature change includes following side using the upper warm area of i-th of warm area as research object
Face: Elema heating, high-temperature region are incoming/bringing into low-temperature space heat transfer, atmosphere/takes out of, bowl and material are brought into/taken out of, moisture
Evaporation endothermic, material consumption of chemical reaction, the heat dissipation of kiln wall；According to the relationship opening relationships formula (1) of temperature change and energy variation:
Wherein Qi1,Qi2,Qi3Respectively indicate the internal energy variation, sensible heat variation and heat transfer of the upper warm area of i-th of warm area
Variation, a indicate the coefficient of heat transfer；
Q is obtained according to energy variationi1,Qi2,Qi3, it is substituted into (1) formula and is simplified, obtain computation model (2):
Wherein, Pi1It (t) is warm area heating power on i-th of warm area, xi1,xi2Respectively i-th of warm area up/down warm area temperature
Degree, x(i-1)1,x(i-1)2Indicate (i-1)-th warm area up/down warm area temperature, φ (xi1(t)) warm area consumption of chemical reaction in expression
Heat, viThe atmosphere flow that i-th of warm area is passed through；
The computation model of the lower warm area of i-th of warm area can be similarly obtained, finally carries out simplifying processing for two computation models, obtain
To final mechanism model (3):
Wherein, xi1,xi2Respectively indicate i-th of warm area warm area temperature up and down；ui1=Pi1Δt,ui2=Pi2Δ t is respectively indicated
The heat generated in warm area heating rod Δ t above and below i-th of warm area；viIndicate the atmosphere flow that i-th of warm area is passed through；x(i-1)1,
x(i-1)2Indicate the temperature of the previous warm area of i-th of warm area or more warm area, x(i+1)1,x(i+1)2Warm area above and below the latter warm area
Temperature；φ(xi1), φ (xi2) indicate i-th of warm area up/down warm area consumption of chemical reaction heat, it is other for system it is to be identified
Parameter；
Again, it is contemplated that Roller Conveying Kiln for Temperature constantly changes, and the heat for reacting consumption can not be by a specific relational expression
Indicate, but in constant pressure, constant volume and under being passed through atmosphere flow certain condition, the energy of consumption of chemical reaction only with current temperature
Area's temperature is related, it is possible to function related with temperature is expressed as, using gaussian kernel function to the heat of consumption of chemical reaction
Carry out piecewise fitting, such as (4) formula:
Wherein, xi1,xi2Indicate i-th of warm area up/down warm area temperature；x′i1,x′i2Indicate up/down warm area waypoint temperature,
xmax,xminIndicate warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minIndicate that warm area temperature is most under i-th of warm area
Greatly, minimum value, αi, βiRecognize coefficient.
Two computation models are carried out certain simplifying to handle, obtain final mechanism model (5):
Wherein, xi1,xi2Respectively indicate i-th of warm area up/down warm area temperature；ui1=Pi1Δt,ui2=Pi2Δ t distinguishes table
Show i-th of warm area interior heat generated of warm area heating rod Δ t up and down；viIndicate the atmosphere flow that i-th of warm area is passed through；x(i-1)1,
x(i-1)2,x(i+1)1,x(i+1)2Indicate the temperature of i-th of warm area front and back warm area；x′i1, x 'i2Indicate up/down warm area waypoint temperature,
xmax,xminIndicate warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minIndicate that warm area temperature is most under i-th of warm area
Greatly, minimum value；Other is system parameter to be identified；
Finally mechanism model parameter is carried out using least-squares parameter discrimination method using the sample data of lane database
Identification, and simulating, verifying；
3) temperature error of the nonlinear time-varying process returned based on local weighted core principle component predicts modeling: according to roller-way
Kiln sintering process data have high-dimensional, strong nonlinearity and process time-varying characteristics, and Principal Component Analysis, geo-nuclear tracin4 is respectively adopted
And instant learning method, the temperature error for establishing the nonlinear time-varying process returned based on local weighted core principle component predict mould
Type；
The sample data of lane database is classified first: training sample verifies sample, test sample, according to each sample
The distance between test sample size, i.e. similarity obtain weight coefficient, wherein between historical sample and test sample away from
From and specified weight value, using (6) formula:
Wherein, xiFor historical data, xqFor test sample, diIndicate the distance between historical sample and test sample, σ table
Show the parameter for adjusting weight with distance change speed, wiIndicate specified weight value；
Construct the weighting training sample φ after the projection of non-linear higher dimensional spacew(xi), calculate weighting covariance matrix
(7):
Secondly, making the result obtained that can more react true reality to extract data non-linear partial, Gaussian kernel letter is introduced
Several pairs of nonlinear characteristics extract, that is, calculate each sample in the score vector of projecting direction, including training sample and survey
The score vector of sample sheet, shown in calculation formula (8):
Wherein, TW,K,tq W,KRespectively indicate training sample, test sample score vector, Kw,Kq wRespectively indicate training sample,
Test sample projects nuclear matrix, αd W,KExpression projects to the feature vector of d dimension space；
Then, the least square regression model between output variable and nonlinear characteristic is established, calculation formula (9):
Finally training sample is used as using the data of lane database as the difference that input, actual temperature and mechanism model export
This, optimizes identification, and simulating, verifying to model parameter；
4) Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach: firstly, utilizing the sample of database
Data carry out mechanism model parameter using least-squares parameter discrimination method, and emulation obtains model output；Then, with mechanism
The input of model is inputted as data model, using actual temperature and the difference of mechanism model output as the output of data model,
It establishes new sample data with this to optimize data model parameters, emulation obtains temperature error prediction output；Finally, by machine
The error prediction output that the output and data model that reason model obtains obtain is summed, and the temperature prediction for finally obtaining integrated model is defeated
Out.
The invention has the following beneficial effects:
1) mechanism model established by the present invention contains more shadows in sintering process compared to one order time delay system
The factor of sound, finally obtained result more closing to reality；
2) it in view of roller kilns sintering is a sufficiently complex process, can not be described by a single mechanism model whole
A sintering process, and mechanism model is that can inevitably have model error in this way, however a nothing in model by centainly simplifying
The Relationship Comparison between influence factor and error that method embodies is complicated, can not be retouched by determining relationship founding mathematical models
It states, in order to obtain better prediction result, using the input of mechanism model as input, is exported with actual temperature and mechanism model
Difference establishes data-driven model as training sample, which supplements the important factor in order that mechanism model can not embody,
The reality for making whole system include is richer, and it is more accurate to obtain final output result；
3) output and data model that obtain mechanism model temperature error prediction output summation, it is available more
Accurate prediction output.The state change of process can be preferably tracked using this model, provided very for Roller Conveying Kiln for Temperature control
Good directive function, to improve production quality and qualification rate.
Detailed description of the invention
Fig. 1 is that the Roller Conveying Kiln for Temperature that mechanism of the present invention is combined with data predicts integrated modular concept figure；
Fig. 2 is the effect diagram of the 2nd warm area mechanism model output of the invention；
Fig. 3 is the effect diagram of the 3rd warm area mechanism model output of the invention；
Fig. 4 is the effect diagram of warm area error prediction data model output on the 2nd warm area of the invention；
Fig. 5 is the effect diagram of warm area error prediction data model output on the 3rd warm area of the invention；
Fig. 6 is the effect diagram of the 2nd warm area Roller Conveying Kiln for Temperature prediction integrated model output of the present invention；
Fig. 7 is the effect diagram of the 3rd warm area Roller Conveying Kiln for Temperature prediction integrated model output of the present invention.
Specific embodiment
In order to better illustrate the present invention, hereby with a preferred embodiment, and attached drawing is cooperated to elaborate the present invention, specifically
It is as follows:
Embodiment 1
Step 1: data prediction: carrying out arrangement early period to roller kilns process operation data, the data including display mistake,
The data etc. of missing, are stored in created database after putting in order, mainly include following data: roller in the database
I-th of warm area up/down warm area temperature x of road kilni1,xi2, up/down warm area heating power Pi1,Pi2, i-th of warm area front and back warm area temperature
Respectively x(i-1)1,x(i-1)2,x(i+1)1,x(i+1)2, it is passed through the atmosphere flow v of each warm areai, the mobile speed V of material and bowl；
The data obtained call it is a certain amount of be used as training sample data, for recognizing building for model parameter and data error prediction model
It is vertical；
Step 2: firstly, being analysed in depth by influencing temperature variation factors to the i-th 1 warm areas, temperature change is mainly by such as
The influence of lower three aspects
1. internal heat changes:
2. sensible heat changes: Qi2=α0Ci0vi1xq0+Ci1mi1x(i-1)1-Ci2vi2xq1-Ci3mi2xi1(t)
3. heat transfer variation:
Qi3=ωi1(x(i+1)1(t)-xi1(t))-ωi2(xi1(t)-x(i-1)1(t))-ωi3(xi1(t)-xi2(t))-ωi4
(xi1(t)-xq2)
Wherein, internal heat variation is made of Elema heating, vapor heat dissipation and chemical reaction heat dissipation；Sensible heat variation
The heat that the heat brought by atmosphere, material, bowl is taken away with atmosphere, material, bowl is constituted；Heat transfer variation refer to high-temperature region to
The thermal change of low temperature block transitive.Pi1(t) be the i-th 1 warm area t moments power, ωi1, ωi2,ωi3, ωi4Indicate temperature with
Energy conversion factor；x(i-1)1,x(i-1)2,x(i+1)1,x(i+1)2Indicate (i-1)-th, i+1 warm area up/down warm area t moment temperature；xi1,
xi2Indicate the corresponding temperature of i-th of warm area up/down warm area t moment, α0, C0, Ci0, Ci1, Ci2, Ci3, xq0, xq1, xq2, mi0, mi1,
mi2Regard constant as under certain condition；vi1Indicate the atmosphere that i-th of the warm area of a hour atmosphere in normal conditions is passed through
Flow.vi2Indicate the atmosphere flow of i-th of warm area discharge
Secondly, according to the relationship opening relationships formula (1) of temperature change and energy variation:
Three's relationship, which is substituted into above formula, and carries out certain simplification can obtain the i-th 1 following computation models of warm area temperature
Wherein, Pi1It (t) is warm area heating power on i-th of warm area, xi1,xi2Respectively i-th of warm area up/down warm area temperature
Degree, x(i-1)1(t), x(i+1)1(t) warm area temperature on (i-1)-th, i+1 warm area, v are indicatediThe atmosphere flow that i-th of warm area is passed through,
φ(xi1(t)) in expression warm area consumption of chemical reaction heat.
The i-th 2 following computation models of warm area temperature (3) can similarly be obtained:
Wherein, Pi2It (t) is warm area heating power under i-th of warm area, xi1,xi2Respectively i-th of warm area up/down warm area temperature
Degree, x(i-1)2(t), x(i+1)2(t) warm area temperature on (i-1)-th, i+1 warm area, v are indicatediThe atmosphere flow that i-th of warm area is passed through,
φ(xi2(t)) heat of lower warm area consumption of chemical reaction is indicated.
Again, it is contemplated that Roller Conveying Kiln for Temperature constantly changes, and the heat for reacting consumption can not be by a specific relational expression
Indicate, but in constant pressure, constant volume and under being passed through atmosphere flow certain condition, the energy of consumption of chemical reaction only with current temperature
Area's temperature is related, it is possible to function related with temperature is expressed as, using gaussian kernel function to the heat of consumption of chemical reaction
Carry out piecewise fitting, such as (4) formula:
Wherein, xi1,xi2Indicate i-th of warm area up/down warm area temperature；x′i1,x′i2Indicate up/down warm area waypoint temperature,
xmax,xminIndicate warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minIndicate that warm area temperature is most under i-th of warm area
Greatly, minimum value, αi, βiRecognize coefficient.
Two computation models are carried out certain simplifying to handle, obtain final mechanism model (5):
Wherein, xi1,xi2Respectively indicate i-th of warm area up/down warm area temperature；ui1=Pi1Δt,ui2=Pi2Δ t distinguishes table
Show i-th of warm area interior heat generated of warm area heating rod Δ t up and down；viIndicate the atmosphere flow that i-th of warm area is passed through；x(i-1)1,
x(i-1)2,x(i+1)1,x(i+1)2Indicate the temperature of i-th of warm area front and back warm area；x′i1, x 'i2Indicate up/down warm area waypoint temperature,
xmax,xminIndicate warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minIndicate that warm area temperature is most under i-th of warm area
Greatly, minimum value；Other is system parameter to be identified；
Finally mechanism model parameter is carried out using least-squares parameter discrimination method using the sample data of lane database
Identification, and simulating, verifying, if Fig. 2, Fig. 3 are the output of the 2nd, 3 warm area mechanism models and actual temperature effect picture, wherein cyan, black
Color curve respectively indicates the 2nd, 3 warm areas warm area actual temperature up and down, and red, blue curve respectively indicates the 2nd, 3 warm areas temperature up and down
Area's mechanism model exports result；Temperature is exported and is stored in database with data such as the differences of actual temperature.
Step 3: the temperature error to generate to mechanism model carries out effective compensation, needs the temperature generated to mechanism model
Error establishes data model.The sample data of lane database is classified first: training sample, verifying sample, test sample,
In, the speed of input of the data model input comprising mechanism model, adjacent warm area temperature and material movement.According to each sample
The distance between test sample size, i.e. similarity obtain weight coefficient, wherein between historical sample and test sample away from
From and specified weight value, using formula (6):
Wherein, xiFor historical data, xqFor test sample, diIndicate the distance between historical sample and test sample, σ table
Show the parameter for adjusting weight with distance change speed, wiIndicate specified weight value；
The weighting training sample after the projection of non-linear higher dimensional space is constructed, weighting covariance matrix (7) is calculated:
Secondly, making the result obtained that can more react true reality to extract data non-linear partial, Gaussian kernel letter is introduced
Several pairs of nonlinear characteristics extract, that is, calculate each sample in the score vector of projecting direction, including training sample and look into
The score vector of sample is ask, calculation formula (8):
Again, the least square regression model between output variable and nonlinear characteristic is established, calculation formula (9):
Finally data model parameters are optimized using database sample data, and obtain temperature error prediction output,
Fig. 4, Fig. 5 are that warm area temperature error predicts output effect schematic diagram on the 2nd, 3 warm areas, and wherein red line indicates prediction result, blue
Color table shows test sample.
Step 4: more accurate temperature prediction output in order to obtain combines mechanism model with data model, establishes
Roller Conveying Kiln for Temperature predicts integrated model, and Fig. 1 shows the Roller Conveying Kiln for Temperature that mechanism is combined with data to predict integrated modular concept figure；
The temperature error prediction output summation of output and data model that mechanism model is obtained, available more accurate prediction
Output, Fig. 6,7 are that warm area Roller Conveying Kiln for Temperature predicts the effect diagram that integrated model exports on the 2nd, 3 warm area.From result point
Analysis is controlled for Roller Conveying Kiln for Temperature and provides good guidance it is found that can preferably be tracked the state change of process using this model
Effect, to improve production quality and qualification rate.
Disclosed above is only the specific embodiment of the application, the skill of however, this application is not limited to this any this field
What art personnel can think variation, should all fall in the protection domain of the application.
Claims (1)
1. a kind of modeling method for the Roller Conveying Kiln for Temperature prediction for combining mechanism with data, it is characterised in that including walking as follows
It is rapid:
1) data processing: arranging roller kilns process operation data, be stored in created database, the data
It include following data: warm area temperature x on i-th of warm area of roller kilns in libraryi1, lower warm area temperature xi2, warm area adds on i-th of warm area
Thermal power Pi1, lower warm area heating power Pi2, warm area temperature is respectively x to the previous warm area of i-th of warm area up and down(i-1)1,
x(i-1)2, warm area temperature is respectively x to the latter warm area up and down(i+1)1,x(i+1)2, it is passed through the atmosphere flow v of each warm areai, material and
The mobile speed V of bowl；The data obtained is as training sample data, for recognizing model parameter and data error prediction model
Foundation；
2) modelling by mechanism based on temperature Yu energy variation relationship: temperature of charge can not be measured directly, and thermocouple is measured temperature
It is regarded as entirely going up warm area or lower warm area temperature, roller kilns sintering is the process of slow time-varying, and sampling point power is considered as Δ t=
Power in 5min, it is assumed that each warm area pressure is constant；
Secondly, the factor for influencing temperature change includes the following aspects using the upper warm area of i-th of warm area as research object:
Elema heating, high-temperature region are incoming/bringing into low-temperature space heat transfer, atmosphere/takes out of, bowl and material are brought into/taken out of, moisture evaporation
Heat absorption, the heat dissipation of material consumption of chemical reaction, kiln wall；According to the relationship opening relationships formula (1) of temperature change and energy variation:
Wherein Qi1,Qi2,Qi3The internal energy variation, sensible heat variation and heat transfer for respectively indicating the upper warm area of i-th of warm area become
Change, a indicates the coefficient of heat transfer；
Q is obtained according to energy variationi1,Qi2,Qi3, it is substituted into (1) formula and is simplified, obtain computation model (2):
Wherein, Pi1It (t) is warm area heating power on i-th of warm area, xi1,xi2Respectively i-th of warm area up/down warm area temperature,
x(i-1)1,x(i-1)2Indicate (i-1)-th warm area up/down warm area temperature, φ (xi1(t)) in expression warm area consumption of chemical reaction heat
Amount, viThe atmosphere flow that i-th of warm area is passed through；
The computation model of the lower warm area of i-th of warm area can be similarly obtained, finally carries out simplifying processing for two computation models, obtain most
Whole mechanism model (3):
Wherein, xi1,xi2Respectively indicate i-th of warm area warm area temperature up and down；ui1=Pi1Δt,ui2=Pi2Δ t respectively indicates i-th
The heat generated in warm area heating rod Δ t above and below a warm area；viIndicate the atmosphere flow that i-th of warm area is passed through；x(i-1)1,x(i-1)2
Indicate the temperature of the previous warm area of i-th of warm area or more warm area, x(i+1)1,x(i+1)2The temperature of warm area above and below the latter warm area；
φ(xi1), φ (xi2) indicate i-th of warm area up/down warm area consumption of chemical reaction heat, it is other be system parameter to be identified；
Again, it is contemplated that Roller Conveying Kiln for Temperature constantly changes, and the heat for reacting consumption can not be by a specific relational expression come table
Show, but in constant pressure, constant volume and under being passed through atmosphere flow certain condition, the energy of consumption of chemical reaction only with current warm area temperature
It spends related, it is possible to be expressed as function related with temperature, be carried out using heat of the gaussian kernel function to consumption of chemical reaction
Piecewise fitting, such as (4) formula:
Wherein, xi1,xi2Indicate i-th of warm area up/down warm area temperature；x′i1,x′i2Indicate up/down warm area waypoint temperature, xmax,
xminIndicate warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minIndicate warm area maximum temperature under i-th of warm area, most
Small value, αi, βiRecognize coefficient；
Two computation models are carried out certain simplifying to handle, obtain final mechanism model (5):
Wherein, xi1,xi2Respectively indicate i-th of warm area up/down warm area temperature；ui1=Pi1Δt,ui2=Pi2Δ t respectively indicates i-th
The heat generated in warm area heating rod Δ t above and below a warm area；viIndicate the atmosphere flow that i-th of warm area is passed through；x(i-1)1,
x(i-1)2,x(i+1)1,x(i+1)2Indicate the temperature of i-th of warm area front and back warm area；x′i1, x 'i2Indicate up/down warm area waypoint temperature,
xmax,xminIndicate warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minIndicate that warm area temperature is most under i-th of warm area
Greatly, minimum value；Other is system parameter to be identified；
Finally mechanism model parameter is recognized using least-squares parameter discrimination method using the sample data of lane database,
And simulating, verifying；
3) temperature error of the nonlinear time-varying process returned based on local weighted core principle component predicts modeling: according to roller kiln burning
Tie process data have high-dimensional, strong nonlinearity and process time-varying characteristics, be respectively adopted Principal Component Analysis, geo-nuclear tracin4 and
Instant learning method establishes the temperature error prediction model of the nonlinear time-varying process returned based on local weighted core principle component；
The sample data of lane database is classified first: training sample verifies sample, and test sample according to each sample and is surveyed
The distance between sample sheet size, i.e. similarity obtain weight coefficient, wherein training sample and test sample in historical sample
The distance between and specified weight value, using (6) formula:
Wherein, xiFor historical data, xqFor test sample, diIndicate the training sample in historical sample and between test sample
Distance, σ indicate to adjust parameter of the weight with distance change speed, wiIndicate specified weight value；
Construct the weighting training sample φ after the projection of non-linear higher dimensional spacew(xi), calculate weighting covariance matrix (7):
Secondly, making the result obtained that can more react true reality to extract data non-linear partial, gaussian kernel function pair is introduced
Nonlinear characteristic extracts, that is, calculates each sample in the score vector of projecting direction, including training sample and test specimens
This score vector, shown in calculation formula (8):
Wherein, TW,K,tq W,KRespectively indicate training sample, test sample score vector, Kw,Kq wRespectively indicate training sample, test
Sample projects nuclear matrix, αd W,KExpression projects to the feature vector of d dimension space；
Then, the least square regression model between output variable and nonlinear characteristic is established, calculation formula (9):
Finally using the data of lane database as input, the difference of actual temperature and mechanism model output as training sample,
Identification, and simulating, verifying are optimized to model parameter；
4) Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach: firstly, using the sample data of database,
Mechanism model parameter is carried out using least-squares parameter discrimination method, emulation obtains model output；Then, with mechanism model
Input is inputted as data model, using actual temperature and the difference of mechanism model output as the output of data model, is built with this
It founds new sample data to optimize data model parameters, emulation obtains temperature error prediction output；Finally, by mechanism model
The error prediction output that obtained output and data model obtains is summed, and the temperature prediction output of integrated model is finally obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710250996.5A CN107038307B (en) | 2017-04-18 | 2017-04-18 | The Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710250996.5A CN107038307B (en) | 2017-04-18 | 2017-04-18 | The Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107038307A CN107038307A (en) | 2017-08-11 |
| CN107038307B true CN107038307B (en) | 2019-07-30 |
Family
ID=59535518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710250996.5A Active CN107038307B (en) | 2017-04-18 | 2017-04-18 | The Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107038307B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549732B (en) * | 2017-12-19 | 2021-08-24 | 中南大学 | Roller kiln temperature modeling method based on local quadratic weighting kernel principal component regression |
| CN108563121B (en) * | 2018-04-12 | 2021-06-15 | 南京航空航天大学 | Intelligent microwave heating temperature field monitoring method based on historical data |
| CN108920858B (en) * | 2018-07-19 | 2024-01-23 | 成都巴莫科技有限责任公司 | Method for predicting service life of roller kiln heating rod |
| CN112241151A (en) * | 2020-09-25 | 2021-01-19 | 北京索为云网科技有限公司 | Data processing method, device, equipment and medium in industrial operation and maintenance scene |
| CN113177332B (en) * | 2021-03-09 | 2023-02-24 | 广东工业大学 | Rotary kiln sintering temperature prediction method based on combination of mechanism and data |
| CN113190974B (en) * | 2021-04-09 | 2022-06-21 | 广东工业大学 | Roller kiln temperature field multipoint prediction method based on deep learning |
| CN113627064B (en) * | 2021-09-03 | 2023-11-21 | 广东工业大学 | Roller kiln firing zone temperature prediction method based on mechanism and data mixed driving |
| CN114370264B (en) * | 2022-01-11 | 2023-12-15 | 中国石油大学(北京) | Mechanical drilling speed determination and drilling parameter optimization method and device and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102176221A (en) * | 2011-03-16 | 2011-09-07 | 中南大学 | Coke furnace temperature predicting method based on dynamic working conditions in coke furnace heating and burning process |
| CN102269973A (en) * | 2011-04-06 | 2011-12-07 | 中南大学 | Method for vaguely predicting, compensating and controlling tower top temperature during desulfurization of sintering flue gas |
| CN102663219A (en) * | 2011-12-21 | 2012-09-12 | 北京理工大学 | Fuel cell output prediction method and system based on mixing model |
| CN103942426A (en) * | 2014-04-15 | 2014-07-23 | 中南大学 | Ballastless track temperature field prediction method |
| JP2015040333A (en) * | 2013-08-22 | 2015-03-02 | Ｊｆｅスチール株式会社 | Method of predicting temperature of steel material, method of controlling temperature of furnace, temperature prediction device for steel material and furnace temperature controller |
| CN104950681A (en) * | 2015-06-25 | 2015-09-30 | 安徽工业大学 | Fuzzy predictive control system for combustion process of lime kiln as well as control method of system |
-
2017
- 2017-04-18 CN CN201710250996.5A patent/CN107038307B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102176221A (en) * | 2011-03-16 | 2011-09-07 | 中南大学 | Coke furnace temperature predicting method based on dynamic working conditions in coke furnace heating and burning process |
| CN102269973A (en) * | 2011-04-06 | 2011-12-07 | 中南大学 | Method for vaguely predicting, compensating and controlling tower top temperature during desulfurization of sintering flue gas |
| CN102663219A (en) * | 2011-12-21 | 2012-09-12 | 北京理工大学 | Fuel cell output prediction method and system based on mixing model |
| JP2015040333A (en) * | 2013-08-22 | 2015-03-02 | Ｊｆｅスチール株式会社 | Method of predicting temperature of steel material, method of controlling temperature of furnace, temperature prediction device for steel material and furnace temperature controller |
| CN103942426A (en) * | 2014-04-15 | 2014-07-23 | 中南大学 | Ballastless track temperature field prediction method |
| CN104950681A (en) * | 2015-06-25 | 2015-09-30 | 安徽工业大学 | Fuzzy predictive control system for combustion process of lime kiln as well as control method of system |
Non-Patent Citations (1)
| Title |
|---|
| "陶瓷辊道窑的温度场数值模拟及决策分析";常排排;《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》;20101215;全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107038307A (en) | 2017-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107038307B (en) | The Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach | |
| CN104899463B (en) | The method for building up of the classification trend prediction model of blast furnace molten iron silicon content four and application | |
| CN108549732B (en) | Roller kiln temperature modeling method based on local quadratic weighting kernel principal component regression | |
| Li et al. | Dynamic time features expanding and extracting method for prediction model of sintering process quality index | |
| CN110991011A (en) | Transformer real-time hot spot temperature prediction method | |
| CN108549789B (en) | Integrated modeling method for ternary cathode material batching system | |
| CN109359723A (en) | Based on the converter terminal manganese content prediction technique for improving regularization extreme learning machine | |
| CN115620846A (en) | Preparation and control method of active manganese material | |
| Wang et al. | An integrated CBR model for predicting endpoint temperature of molten steel in AOD | |
| Geng et al. | Prediction of the cement grate cooler pressure in the cooling process based on a multi-model fusion neural network | |
| Liu et al. | XGBoost-based model for predicting hydrogen content in electroslag remelting | |
| Dakshinamoorthy et al. | Estimating battery temperature in dynamic driving conditions using physics informed neural networks | |
| Jiang et al. | A novel intelligent monitoring method for the closing time of the taphole of blast furnace based on two-stage classification | |
| Tian et al. | Application of genetic algorithm combined with BP neural network in soft sensor of molten steel temperature | |
| Tian et al. | A new incremental learning modeling method based on multiple models for temperature prediction of molten steel in LF | |
| CN103160629B (en) | Method for forecasting heat tendency of blast furnace | |
| CN115718883A (en) | Thermal early warning method and device for battery energy storage system | |
| Huang et al. | SVM-based fuzzy rules acquisition system for pulsed GTAW process | |
| Chen | Enhancing Validity of Green Building Information Modeling with Artificial-neural-network-supervised Learning--Taking Construction of Adaptive Building Envelope Based on Daylight Simulation as an Example. | |
| Luo et al. | Temperature prediction of roller kiln based on mechanism and SSA-ELM data-driven integrated model | |
| Luo et al. | A Hybrid Modeling Method for Aluminum Smelting Process Based on a Hybrid Strategy-Based Sparrow Search Algorithm | |
| Huang et al. | Recognition of Converter Steelmaking State Based on Convolutional Recurrent Neural Networks | |
| Zhang et al. | The research of end-point prediction based on combination model of electric arc furnace | |
| Jiang et al. | Reinforcement learning for blast furnace ironmaking operation with safety and partial observation considerations | |
| Wu et al. | Feature selection of Wrapper based on GA and prediction of Burning Through Point of integrated multi-kernel support vector 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |