CN107038307A - Mechanism predicts integrated modelling approach with the Roller Conveying Kiln for Temperature that data are combined - Google Patents
Mechanism predicts integrated modelling approach with the Roller Conveying Kiln for Temperature that data are combined Download PDFInfo
- Publication number
- CN107038307A CN107038307A CN201710250996.5A CN201710250996A CN107038307A CN 107038307 A CN107038307 A CN 107038307A CN 201710250996 A CN201710250996 A CN 201710250996A CN 107038307 A CN107038307 A CN 107038307A
- Authority
- CN
- China
- Prior art keywords
- warm area
- temperature
- model
- data
- sample
- 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
-
- 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 prediction integrated modelling approach for being combined mechanism with data, by influenceing the factor analysis of temperature change, from temperature change and the angle of energy, setting up mechanism model；Then consider that roller kilns sintering is a sufficiently complex process, whole sintering process can not be described by a single mechanism model, and mechanism model is there is model error by simplifying, data model is set up to be predicted model error, mechanism output is made up with this, i.e., the error prediction model of the nonlinear time-varying process returned based on local weighted core principle component is set up by the use of error as training sample；Last mechanism model is combined with data model and sets up Roller Conveying Kiln for Temperature prediction integrated model.The model obtained using the present invention can preferably track status of processes change, good directive function be provided for Roller Conveying Kiln for Temperature control, so as to improve production quality and qualification rate.
Description
Art
The invention belongs to roller kilns field of smelting, and in particular to Roller Conveying Kiln for Temperature predicts integrated modelling approach
Background technology
Lithium battery has that operating voltage is high, specific energy is big, has extended cycle life, it is lightweight, low in the pollution of the environment the features such as, 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 that, using roller kilns as production platform, 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, with the spy such as energy consumption is low, firing period is short, furnace temperature decision is good
Point, it is also the distributed system of a heat flow field in addition, is divided into warming-up section, constant temperature zone and the Ge great areas of cooling section three, Mei Ge great
Area is divided into some 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, it is the necessary condition for ensureing product quality to maintain temperature stabilization.
At present, limited by work condition environment, the operation information such as oxygen flow distribution, burden distribution inside roller kilns and process
Parameter is difficult to obtain, and partial differential equation have solving complexity, known conditions requirement, single from temperature field, stream
Angularly set out field, it is difficult to set up accurate partial differential equation mathematical modeling.It is near in order to obtain Roller Conveying Kiln for Temperature variation tendency
Researcher generally makees approximate model as the model of system using one order time delay system according to the characteristics of roller kilns to temperature over year,
But the result that this simplified model is estimated temperature has larger error with actual temperature value, so setting up one can solve
It is convenient, the problem of mechanism model that Roller Conveying Kiln for Temperature can be preferably estimated again is current to be resolved.Yet with sintering process
Complexity, mechanism model can not embody the factor of had an impact temperature, and obtained result can exist unavoidably with actual temperature to be missed
Difference, therefore, in order to obtain more accurate Temperature estimate value, it is also to need to solve that the error that model is produced, which is predicted, in advance
A big problem.
The content of the invention
It is an object of the invention to provide a kind of Roller Conveying Kiln for Temperature prediction integrated moulding being combined based on mechanism with data
Method, i.e., set up mechanism model from the angle of temperature change and energy variation, then utilizes mechanism model output and reality
The difference of temperature sets up data model as training sample, and error is predicted, finally by mechanism model and data model
Output summation is exported as final temperature, is used for solving the problem of prior art is present with this.
It is a kind of that integrated modelling approach is predicted with the Roller Conveying Kiln for Temperature that data are combined based on mechanism, comprise the following steps：
1) data processing step：Roller kilns process operation data are arranged, created data are stored in
In storehouse；
2) modelling by mechanism based on temperature Yu energy variation relation：Temperature of charge can not direct measurement, 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 into Δ t
Power in=5min, it is assumed that each warm area pressure is constant；
Secondly, using the upper warm area of i-th of warm area as research object, the factor of influence temperature change includes following side
Face：Elema heating, high-temperature region incoming/being conducted heat to low-temperature space, atmosphere is brought into/are taken out of, bowl and material are brought into/taken out of, moisture
Evaporation endothermic, material consumption of chemical reaction, the radiating of kiln wall；According to temperature change and the relation opening relationships formula (1) of energy variation：
Wherein Qi1,Qi2,Qi3The internal energy change, sensible heat change and heat transfer of the upper warm area of i-th of warm area are represented respectively
Change, a represents the coefficient of heat transfer；
Q is obtained according to energy variationi1,Qi2,Qi3, substituted into (1) formula and simplified, obtain computation model (2)：
Wherein, Pi1(t) it is warm area heating power, x on i-th of warm areai1,xi2Respectively i-th warm area up/down warm area temperature
Degree, x(i-1)1,x(i-1)2Represent the i-th -1 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 by two computation models, obtains
To final mechanism model (3)：
Wherein, xi1,xi2Warm area temperature above and below i-th of warm area is represented respectively；ui1=Pi1Δt,ui2=Pi2Δ t is represented respectively
The heat produced above and below i-th of warm area in warm area heating rod Δ t；viRepresent the atmosphere flow that i-th of warm area is passed through；x(i-1)1,
x(i-1)2Represent the temperature of warm area above and below the previous warm area of i-th of warm area, x(i+1)1,x(i+1)2Warm area above and below latter warm area
Temperature；φ(xi1), φ (xi2) represent 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 is continually changing, the heat of reaction consumption can not pass through a specific relational expression
To represent, but in constant pressure, constant volume and be passed through under atmosphere flow certain condition, the energy of consumption of chemical reaction only with current temperature
Area's temperature is relevant, it is possible to be expressed as the function relevant with temperature, utilizes heat of the gaussian kernel function to consumption of chemical reaction
Carry out piecewise fitting, such as (4) formula：
Wherein, xi1,xi2Represent i-th of warm area up/down warm area temperature；x′i1,x′i2Up/down warm area waypoint temperature is represented,
xmax,xminRepresent warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minRepresent that warm area temperature is most under i-th of warm area
Greatly, minimum value, αi, βiRecognize coefficient.
Two computation models are carried out into certain simplifying to handle, final mechanism model (5) is obtained：
Wherein, xi1,xi2I-th of warm area up/down warm area temperature is represented respectively；ui1=Pi1Δt,ui2=Pi2Δ t distinguishes table
Show the heat produced above and below i-th of warm area in warm area heating rod Δ t；viRepresent 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)2Represent the temperature of warm area before and after i-th of warm area；x′i1, x 'i2Up/down warm area waypoint temperature is represented,
xmax,xminRepresent warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minRepresent 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
Klining knot process data has high-dimensional, strong nonlinearity and process time-varying characteristics, and PCA, geo-nuclear tracin4 is respectively adopted
And instant learning method, set up the temperature error prediction mould of the nonlinear time-varying process returned based on local weighted core principle component
Type；
The sample data of lane database is classified first：Training sample, verifies sample, test sample, according to each sample
Obtain weight coefficient with the distance between test sample size, i.e. similarity, wherein, between historical sample and test sample away from
From and specified weight value, using (6) formula：
Wherein, xiFor historical data, xqFor test sample, diRepresent the distance between historical sample and test sample, σ tables
Show regulation weight with the parameter of distance change speed, wiRepresent specified weight value；
Build the weighting training sample φ after the projection of non-linear higher dimensional spacew(xi), calculate weighting covariance matrix
(7)：
Secondly, in order to extract data non-linear partial, true reality can more be reacted by making the result of acquisition, introduce Gaussian kernel letter
It is several that nonlinear characteristic is extracted, that is, calculate score vector of each sample in projecting direction, including training sample and survey
The score vector of sample sheet, shown in calculation formula (8)：
Wherein, TW,K,tq W,KTraining sample, test sample score vector, K are represented respectivelyw,Kq wRespectively represent training sample,
Test sample projects nuclear matrix, αd W,KExpression projects to the characteristic vector of d dimension spaces；
Then, the least square regression model set up between output variable and nonlinear characteristic, calculation formula (9)：
Finally by the use of the data of lane database as input, the difference that actual temperature is exported with mechanism model is used as training sample
This, identification, and simulating, verifying are optimized to model parameter；
4) mechanism predicts integrated modelling approach with the Roller Conveying Kiln for Temperature that data are combined：First, the sample of database is utilized
Data, are carried out using least-squares parameter discrimination method to mechanism model parameter, 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,
New sample data is set up with this to optimize data model parameters, emulation obtains temperature error prediction output；Finally, by machine
The error prediction output that the output that reason model is obtained is obtained with data model is summed, and the temperature prediction for finally giving integrated model is defeated
Go out.
The present invention has the advantages that：
1) mechanism model that the present invention is set up, compared to one order time delay system, contains more shadows in sintering process
The factor of sound, the result finally given more closing to reality；
2) consider that roller kilns sintering is a sufficiently complex process, it is impossible to describe whole by a single mechanism model
Individual sintering process, and mechanism model is but the nothing in model by necessarily simplifying, can so there is model error unavoidably
Relationship Comparison between influence factor and error that method embodies is complicated, it is impossible to retouched by the relation founding mathematical models of determination
State, in order to preferably be predicted the outcome, using the input of mechanism model as input, exported with actual temperature and mechanism model
Difference sets up data-driven model as training sample, and the model supplements the important factor in order that mechanism model can not embody,
The reality for including whole system is more rich, obtains final output result more accurate；
3) output and the temperature error prediction output summation of data model obtained mechanism model, can be obtained more
Accurate prediction output.Status of processes change can be preferably tracked using this model, is provided very for Roller Conveying Kiln for Temperature control
Good directive function, so as to improve production quality and qualification rate.
Brief description of the drawings
Fig. 1 is that mechanism of the present invention predicts integrated modular concept figure with the Roller Conveying Kiln for Temperature that data are combined；
Fig. 2 is the effect diagram of the 2nd warm area mechanism model output of the present invention；
Fig. 3 is the effect diagram of the 3rd warm area mechanism model output of the present 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.
Embodiment
For the present invention is better described, hereby with a preferred embodiment, and accompanying drawing is coordinated to elaborate the present invention, specifically
It is as follows：
Embodiment 1
Step 1：Data prediction：Roller kilns process operation data are carried out with early stage arrangement, includes the data of display mistake,
Data of missing etc., are stored in after putting in order in created database, and following data are mainly included in the database：Roller
I-th of warm area up/down warm area temperature x of road kilni1,xi2, up/down warm area heating power Pi1,Pi2, warm area temperature before and after i-th of warm area
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 speed V that material and bowl are moved；
The data obtained call it is a certain amount of as training sample data, for building for identification model parameter and data error forecast model
It is vertical；
Step 2：First, by influenceing temperature variation factors to analyse in depth 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 change：
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 change is heated by Elema, vapor heat dissipation and chemical reaction heat dissipation are constituted；Sensible heat changes
The heat that the heat and atmosphere brought into by atmosphere, material, bowl, material, bowl are taken away is constituted；Heat transfer change refer to high-temperature region to
The thermal change of low temperature block transitive.Pi1(t) be the i-th 1 warm area ts power, ωi1, ωi2,ωi3, ωi4Represent temperature with
Energy conversion factor；x(i-1)1,x(i-1)2,x(i+1)1,x(i+1)2Represent i-th -1, i+1 warm area up/down warm area t temperature；xi1,
xi2Represent the corresponding temperature of i-th of warm area up/down warm area t, α0, C0, Ci0, Ci1, Ci2, Ci3, xq0, xq1, xq2, mi0, mi1,
mi2Regard constant as under certain condition；vi1Represent the atmosphere that i-th of the warm area of a hour atmosphere in normal conditions is passed through
Flow.vi2Represent the atmosphere flow of i-th of warm area discharge
Secondly, according to temperature change and the relation opening relationships formula (1) of energy variation：
Three's relationship is substituted into above formula and carries out certain simplification and can obtain the i-th 1 warm area temperature model is calculated as below
Wherein, Pi1(t) it is warm area heating power, x on i-th of warm areai1,xi2Respectively i-th warm area up/down warm area temperature
Degree, x(i-1)1(t), x(i+1)1(t) warm area temperature, v on the i-th -1, i+1 warm area are representediThe 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 warm area temperature can similarly be obtained model (3) is calculated as below：
Wherein, Pi2(t) it is warm area heating power, x under i-th of warm areai1,xi2Respectively i-th warm area up/down warm area temperature
Degree, x(i-1)2(t), x(i+1)2(t) warm area temperature, v on the i-th -1, i+1 warm area are representediThe atmosphere flow that i-th of warm area is passed through,
φ(xi2(t) heat of lower warm area consumption of chemical reaction) is represented.
Again, it is contemplated that Roller Conveying Kiln for Temperature is continually changing, the heat of reaction consumption can not pass through a specific relational expression
To represent, but in constant pressure, constant volume and be passed through under atmosphere flow certain condition, the energy of consumption of chemical reaction only with current temperature
Area's temperature is relevant, it is possible to be expressed as the function relevant with temperature, utilizes heat of the gaussian kernel function to consumption of chemical reaction
Carry out piecewise fitting, such as (4) formula：
Wherein, xi1,xi2Represent i-th of warm area up/down warm area temperature；x′i1,x′i2Up/down warm area waypoint temperature is represented,
xmax,xminRepresent warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minRepresent that warm area temperature is most under i-th of warm area
Greatly, minimum value, αi, βiRecognize coefficient.
Two computation models are carried out into certain simplifying to handle, final mechanism model (5) is obtained：
Wherein, xi1,xi2I-th of warm area up/down warm area temperature is represented respectively；ui1=Pi1Δt,ui2=Pi2Δ t distinguishes table
Show the heat produced above and below i-th of warm area in warm area heating rod Δ t；viRepresent 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)2Represent the temperature of warm area before and after i-th of warm area；x′i1, x 'i2Up/down warm area waypoint temperature is represented,
xmax,xminRepresent warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minRepresent 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, such as Fig. 2, Fig. 3 are the output of the 2nd, 3 warm area mechanism models and actual temperature design sketch, wherein, it is cyan, black
Color curve represents warm area actual temperature above and below the 2nd, 3 warm areas respectively, and red, blue curve represents warm above and below the 2nd, 3 warm areas respectively
Area's mechanism model output result；By temperature export and with the data such as the difference of actual temperature deposit database.
Step 3：Effective compensation is carried out for the temperature error that is produced to mechanism model, it is necessary to the temperature produced to mechanism model
Error sets up data model.The sample data of lane database is classified first：Training sample, checking sample, test sample, its
In, data model input includes the speed of the inputting of mechanism model, adjacent warm area temperature and material movement.According to each sample
Obtain weight coefficient with the distance between test sample size, i.e. similarity, wherein, between historical sample and test sample away from
From and specified weight value, using formula (6)：
Wherein, xiFor historical data, xqFor test sample, diRepresent the distance between historical sample and test sample, σ tables
Show regulation weight with the parameter of distance change speed, wiRepresent specified weight value；
The weighting training sample after the projection of non-linear higher dimensional space is built, weighting covariance matrix (7) is calculated：
Secondly, in order to extract data non-linear partial, true reality can more be reacted by making the result of acquisition, introduce Gaussian kernel letter
It is several that nonlinear characteristic is extracted, that is, calculate score vector of each sample in projecting direction, including training sample and look into
Ask the score vector of sample, calculation formula (8)：
Again, the least square regression model set up between output variable and nonlinear characteristic, calculation formula (9)：
Finally data model parameters are optimized using database sample data, and obtain temperature error prediction and are exported,
Fig. 4, Fig. 5 are warm area temperature error prediction output effect schematic diagram on the 2nd, 3 warm areas, and wherein red line represents to predict the outcome, blue
Color table shows test sample.
Step 4：In order to obtain more accurate temperature prediction output, mechanism model is combined with data model, set up
Roller Conveying Kiln for Temperature predicts integrated model, and Fig. 1 represents that mechanism predicts integrated modular concept figure with the Roller Conveying Kiln for Temperature that data are combined；
The output and the temperature error prediction output summation of data model that mechanism model is obtained, can obtain more accurately predicting
Output, Fig. 6,7 be warm area Roller Conveying Kiln for Temperature prediction integrated model output on the 2nd, 3 warm areas effect diagram.From result point
Analysis is understood, status of processes change can be preferably tracked using this model, and guidance well is provided for Roller Conveying Kiln for Temperature control
Effect, so as to improve production quality and qualification rate.
Disclosed above is only the specific embodiment of the application, but the application is not limited to the skill of this any this area
What art personnel can think change, 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 being combined mechanism with data, it is characterised in that including following step
Suddenly：
1) data processing：Roller kilns process operation data are arranged, are stored in created database, the data
Storehouse includes following data：Warm area temperature x on i-th of warm area of roller kilnsi1, 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 above and below the previous warm area of i-th of warm area(i-1)1,
x(i-1)2, warm area temperature is respectively x above and below latter warm area(i+1)1,x(i+1)2, it is passed through the atmosphere flow v of each warm areai, material and
The speed V of bowl movement；The data obtained is as training sample data, for identification model parameter and data error forecast model
Foundation；
2) modelling by mechanism based on temperature Yu energy variation relation：Temperature of charge can not direct measurement, thermocouple is measured into 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 into Δ t=
Power in 5min, it is assumed that each warm area pressure is constant；
Secondly, using the upper warm area of i-th of warm area as research object, the factor of influence temperature change includes the following aspects：
Elema heating, high-temperature region incoming/being conducted heat to low-temperature space, atmosphere is brought into/are taken out of, bowl and material are brought into/taken out of, moisture evaporation
Heat absorption, the radiating of material consumption of chemical reaction, kiln wall；According to temperature change and the relation opening relationships formula (1) of energy variation：
Wherein Qi1,Qi2,Qi3Represent that the internal energy change, sensible heat change and heat transfer of the upper warm area of i-th of warm area become respectively
Change, a represents the coefficient of heat transfer；
Q is obtained according to energy variationi1,Qi2,Qi3, substituted into (1) formula and simplified, obtain computation model (2)：
Wherein, Pi1(t) it is warm area heating power, x on i-th of warm areai1,xi2Respectively i-th warm area up/down warm area temperature,
x(i-1)1,x(i-1)2Represent the i-th -1 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 by two computation models, obtains most
Whole mechanism model (3)：
Wherein, xi1,xi2Warm area temperature above and below i-th of warm area is represented respectively；ui1=Pi1Δt,ui2=Pi2Δ t represents i-th respectively
The heat produced above and below individual warm area in warm area heating rod Δ t；viRepresent the atmosphere flow that i-th of warm area is passed through；x(i-1)1,x(i-1)2
Represent the temperature of warm area above and below the previous warm area of i-th of warm area, x(i+1)1,x(i+1)2The temperature of warm area above and below latter warm area；
φ(xi1), φ (xi2) represent 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 is continually changing, the heat of reaction consumption can not be by a specific relational expression come table
Show, but in constant pressure, constant volume and be passed through under atmosphere flow certain condition, the energy of consumption of chemical reaction only with current warm area temperature
Degree is relevant, it is possible to be expressed as the function relevant with temperature, and the heat of consumption of chemical reaction is carried out using gaussian kernel function
Piecewise fitting, such as (4) formula：
Wherein, xi1,xi2Represent i-th of warm area up/down warm area temperature；xi′1,xi′2Represent up/down warm area waypoint temperature, xmax,
xminRepresent warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minRepresent warm area maximum temperature under i-th of warm area, most
Small value, αi, βiRecognize coefficient.
Two computation models are carried out into certain simplifying to handle, final mechanism model (5) is obtained：
Wherein, xi1,xi2I-th of warm area up/down warm area temperature is represented respectively；ui1=Pi1Δt,ui2=Pi2Δ t represents i-th respectively
The heat produced above and below individual warm area in warm area heating rod Δ t；viRepresent 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)2Represent the temperature of warm area before and after i-th of warm area；x′i1, x 'i2Up/down warm area waypoint temperature is represented,
xmax,xminRepresent warm area maximum temperature, minimum value, x ' on i-th of warm areamax,x′minRepresent 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
Knot process data there are high-dimensional, strong nonlinearity and process time-varying characteristics, be respectively adopted PCA, geo-nuclear tracin4 and
Instant learning method, sets up the temperature error forecast 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, test sample, according to each sample with surveying
The distance between sample sheet size, i.e. similarity obtain weight coefficient, wherein, the distance between historical sample and test sample with
And specified weight value, using (6) formula：
Wherein, xiFor historical data, xqFor test sample, diThe distance between historical sample and test sample are represented, σ represents to adjust
Weight is saved with the parameter of distance change speed, wiRepresent specified weight value；
Build the weighting training sample φ after the projection of non-linear higher dimensional spacew(xi), calculate weighting covariance matrix (7)：
Secondly, in order to extract data non-linear partial, true reality can more be reacted by making the result of acquisition, introduce gaussian kernel function pair
Nonlinear characteristic is extracted, that is, calculates score vector of each sample in projecting direction, including training sample and test specimens
This score vector, shown in calculation formula (8)：
Wherein, TW,K,tq W,KTraining sample, test sample score vector, K are represented respectivelyw,Kq wTraining sample, test are represented respectively
Sample projects nuclear matrix, αd W,KExpression projects to the characteristic vector of d dimension spaces；
Then, the least square regression model set up between output variable and nonlinear characteristic, calculation formula (9)：
Finally by the use of the data of lane database as input, the difference that actual temperature is exported with mechanism model as training sample,
Identification, and simulating, verifying are optimized to model parameter；
4) mechanism predicts integrated modelling approach with the Roller Conveying Kiln for Temperature that data are combined：First, 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
Found 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 is obtained with data model is summed, and finally gives the temperature prediction output of integrated model.
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 true CN107038307A (en) | 2017-08-11 |
| CN107038307B 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) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549732A (en) * | 2017-12-19 | 2018-09-18 | 中南大学 | Roller Conveying Kiln for Temperature soft-measuring modeling method based on local secondary Weighted Kernel principal component regression |
| CN108563121A (en) * | 2018-04-12 | 2018-09-21 | 南京航空航天大学 | Microwave heating temperature field intelligent control method based on historical data |
| CN108920858A (en) * | 2018-07-19 | 2018-11-30 | 成都巴莫科技有限责任公司 | A method of prediction roller kilns heating rod service life |
| CN113177332A (en) * | 2021-03-09 | 2021-07-27 | 广东工业大学 | Rotary kiln sintering temperature prediction method based on combination of mechanism and data |
| CN113190974A (en) * | 2021-04-09 | 2021-07-30 | 广东工业大学 | Roller kiln temperature field multipoint prediction method based on deep learning |
| CN113627064A (en) * | 2021-09-03 | 2021-11-09 | 广东工业大学 | Roller kiln sintering zone temperature prediction method based on mechanism and data hybrid driving |
| CN114370264A (en) * | 2022-01-11 | 2022-04-19 | 中国石油大学(北京) | Mechanical drilling speed determination method, mechanical drilling parameter optimization method, mechanical drilling speed determination device, drilling parameter optimization 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 |
|---|
| 常排排: ""陶瓷辊道窑的温度场数值模拟及决策分析"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549732A (en) * | 2017-12-19 | 2018-09-18 | 中南大学 | Roller Conveying Kiln for Temperature soft-measuring modeling method based on local secondary Weighted Kernel principal component regression |
| 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 |
| CN108563121A (en) * | 2018-04-12 | 2018-09-21 | 南京航空航天大学 | Microwave heating temperature field intelligent control method based on historical data |
| CN108920858A (en) * | 2018-07-19 | 2018-11-30 | 成都巴莫科技有限责任公司 | A method of prediction roller kilns heating rod service life |
| 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 |
| CN113177332A (en) * | 2021-03-09 | 2021-07-27 | 广东工业大学 | Rotary kiln sintering temperature prediction method based on combination of mechanism and data |
| 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 |
| CN113190974A (en) * | 2021-04-09 | 2021-07-30 | 广东工业大学 | Roller kiln temperature field multipoint prediction method based on deep learning |
| 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 |
| CN113627064A (en) * | 2021-09-03 | 2021-11-09 | 广东工业大学 | Roller kiln sintering zone temperature prediction method based on mechanism and data hybrid driving |
| 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 |
| CN114370264A (en) * | 2022-01-11 | 2022-04-19 | 中国石油大学(北京) | Mechanical drilling speed determination method, mechanical drilling parameter optimization method, mechanical drilling speed determination device, drilling parameter optimization device and electronic equipment |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107038307B (en) | 2019-07-30 |
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 | |
| CN108549732A (en) | Roller Conveying Kiln for Temperature soft-measuring modeling method based on local secondary Weighted Kernel principal component regression | |
| Han et al. | Endpoint prediction model for basic oxygen furnace steel-making based on membrane algorithm evolving extreme learning machine | |
| Wang et al. | A hybrid ensemble model based on ELM and improved adaboost. RT algorithm for predicting the iron ore sintering characters. | |
| CN104050380A (en) | LF furnace final temperature forecasting method based on Adaboost-PLS-ELM | |
| Hu et al. | Hybrid modeling and online optimization strategy for improving carbon efficiency in iron ore sintering process | |
| CN109359723A (en) | Based on the converter terminal manganese content prediction technique for improving regularization extreme learning machine | |
| CN105574297B (en) | Self adaptation blast furnace molten iron silicon content trend prediction method | |
| CN106096637A (en) | Molten iron silicon content Forecasting Methodology based on the strong predictor of Elman Adaboost | |
| Li et al. | Dynamic time features expanding and extracting method for prediction model of sintering process quality index | |
| Hu et al. | Multi-model ensemble prediction model for carbon efficiency with application to iron ore sintering process | |
| Wang et al. | An integrated CBR model for predicting endpoint temperature of molten steel in AOD | |
| Liu et al. | Temporal hypergraph attention network for silicon content prediction in blast furnace | |
| Jiang et al. | A novel intelligent monitoring method for the closing time of the taphole of blast furnace based on two-stage classification | |
| CN115718883A (en) | Thermal early warning method and device for battery energy storage system | |
| Ning et al. | Integrated modeling for roller kiln temperature prediction | |
| CN103160629B (en) | Method for prediction of blast furnace heat tendency | |
| CN115310348A (en) | Stacking-based grouting amount integrated agent prediction model and prediction method | |
| Jiang et al. | Prediction of FeO content in sintering process based on heat transfer mechanism and data-driven model | |
| Liu et al. | XGBoost-based model for predicting hydrogen content in electroslag remelting | |
| CN113627064A (en) | Roller kiln sintering zone temperature prediction method based on mechanism and data hybrid driving | |
| Jiao et al. | An Intelligent Temperature Prediction Method Based on PSO-ELM | |
| Wu et al. | Feature selection of Wrapper based on GA and prediction of Burning Through Point of integrated multi-kernel support vector machine | |
| Jiang et al. | Reinforcement Learning for Blast Furnace Ironmaking Operation With Safety and Partial Observation Considerations |
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 |