CN112380738A - Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system - Google Patents

Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system Download PDF

Info

Publication number
CN112380738A
CN112380738A CN202011123190.8A CN202011123190A CN112380738A CN 112380738 A CN112380738 A CN 112380738A CN 202011123190 A CN202011123190 A CN 202011123190A CN 112380738 A CN112380738 A CN 112380738A
Authority
CN
China
Prior art keywords
kiln
model
combustion field
rotary
error compensation
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
Application number
CN202011123190.8A
Other languages
Chinese (zh)
Other versions
CN112380738B (en
Inventor
王孝红
张荣丰
路士增
于宏亮
孟庆金
袁铸钢
景绍洪
蒋萍
张强
刘钊
黄冰
刘化果
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Jinan
Original Assignee
University of Jinan
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Jinan filed Critical University of Jinan
Priority to CN202011123190.8A priority Critical patent/CN112380738B/en
Publication of CN112380738A publication Critical patent/CN112380738A/en
Application granted granted Critical
Publication of CN112380738B publication Critical patent/CN112380738B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/048—Fuzzy inferencing
    • 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)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Mathematical Physics (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Molecular Biology (AREA)
  • Fuzzy Systems (AREA)
  • Automation & Control Theory (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Algebra (AREA)
  • Fluid Mechanics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Curing Cements, Concrete, And Artificial Stone (AREA)
  • Muffle Furnaces And Rotary Kilns (AREA)

Abstract

The invention provides a cement rotary kiln combustion field reconstruction error compensation and optimization method, a storage medium and a system. Secondly, aiming at errors existing in the process of reconstructing a combustion field of the rotary cement kiln and calcining in an actual kiln, a data driving thought is adopted, a reconstruction error compensation method of the combustion field of the rotary cement kiln based on a fuzzy reasoning system and a deep neural network is provided, and a reconstruction error compensation model is constructed to compensate and correct temperature errors obtained by the reconstruction model; and finally, improving the modeling precision of the reconstruction error compensation model by adopting an online optimization method of the reconstruction error compensation model based on a rolling optimization idea. The invention can analyze and evaluate the state of the combustion field in the kiln in real time, and solves the problems of low efficiency and low precision in the simulation of the combustion field in the traditional rotary kiln through the real-time correction of simulation data and actual production data.

Description

Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system
Technical Field
The invention relates to the technical field of cement rotary kiln combustion field mechanism simulation, in particular to a cement rotary kiln combustion field reconstruction error compensation and optimization method based on combination of finite element modeling and data driving, a storage medium and a system.
Background
The rotary kiln is the main equipment for cement clinker calcination, and the clinker calcination coal consumption is the main energy consumption of the whole calcination process. The temperature distribution in the rotary kiln directly reflects the combustion state in the kiln, is the comprehensive reflection of the operating parameters of the rotary kiln, and the heat efficiency of the rotary kiln is closely related to the temperature distribution. The method for modeling the temperature of the rotary cement kiln combustion field is researched, an accurate cement clinker calcination process temperature model is established, the rotary cement kiln combustion field is reconstructed, the temperature distribution in the kiln is accurately mastered, a basis and guarantee can be provided for the calcination efficiency optimization control, and the method has important significance for the cement clinker production optimization control and the energy consumption reduction.
At present, the problem of monitoring the temperature distribution in the kiln is difficult to solve by using a sensing technology, the simulation of a small amount of data on the combustion state in the kiln can be realized by finite element simulation, the simulation technology is combined with real-time production data, the digital twin based on mechanism simulation is realized, the problem that the interior of the kiln is not measurable can be fundamentally solved, and the states of material distribution, gas distribution, combustion fields and the like of a production process are analyzed and evaluated in real time. However, due to various uncertain factors such as non-ideal boundary conditions, finite element discretization and the like, modeling errors necessarily exist in the finite element model, and further optimization control of the cement clinker calcination process according to the temperature in the kiln is restricted, so that the aims of improving the calcination efficiency and reducing the coal consumption are difficult to achieve.
Disclosure of Invention
The invention provides a cement rotary kiln combustion field reconstruction error compensation and optimization method, a storage medium and a system.
The invention provides a method for compensating and optimizing the reconstruction error of a rotary cement kiln combustion field, which comprises the following steps:
step 1: establishing a finite element model of a cement rotary kiln combustion field;
step 2: acquiring temperature simulation data of the finite element model; the temperature simulation data is original data obtained by performing finite element modeling simulation on the rotary kiln combustion field and performing convergence judgment;
and step 3: acquiring internal relation among the combustion efficiency of the rotary cement kiln, operation variables and a combustion environment, and extracting characteristic parameter data related to the combustion efficiency; the characteristic quantity data comprises online real-time parameters, offline laboratory parameters and combustion field reconstruction information parameters;
and 4, step 4: using the selected characteristic parameter data as a modeling parameter of the error compensation model; designing a cement rotary kiln combustion field reconstruction error compensation model based on a fuzzy inference system and a deep neural network mixing method, and analyzing an error relation between a CFD reconstruction combustion field and an actual combustion process;
and 5: performing online optimization on the cement rotary kiln combustion field reconstruction error compensation model by adopting an online optimization algorithm, and correcting simulation data in real time by combining actual production data; and (4) performing online optimization on the combustion field reconstruction error compensation model established in the step (4) by adopting a rolling optimization idea, so that the output of the model compensates the combustion field reconstruction error in real time along with the change of the working condition, and performing model verification by using the real-time data of the rotary cement kiln.
Still other embodiments of the present invention further provide a storage medium, where the storage medium stores program information, and after reading the program information, a computer executes any one of the methods for compensating and optimizing the reconstruction error of the combustion field of the rotary cement kiln.
Still other embodiments of the present invention provide a system for compensating and optimizing a reconstruction error of a combustion field of a rotary cement kiln, including: the system comprises at least one processor and at least one memory, wherein program information is stored in the at least one memory, and the at least one processor reads the program information and then executes the reconstruction error compensation and optimization method for the rotary cement kiln combustion field.
Compared with the prior art, the technical scheme provided by the invention at least has the following effects: the method has the advantages that the combustion field reconstruction error compensation model is constructed by adopting online real-time parameters and offline laboratory parameters related to the combustion state in the kiln, error compensation correction is carried out on temperature simulation data obtained by the combustion field reconstruction model, finite element modeling errors caused by non-ideal boundary conditions, finite element discretization, nonlinear characteristics and the like can be effectively reduced, and the finite element modeling precision is improved; the combustion field reconstruction error compensation model is optimized on line through a rolling optimization thought and a sliding window technology, the problem that the combustion field reconstruction error fluctuates along with the change of working conditions is effectively solved, the timeliness of the error compensation model is ensured, the model output compensates the combustion field reconstruction error in real time along with the change of the working conditions, the modeling precision of the reconstruction error compensation model is improved, and theory and data support is provided for realizing the calcination efficiency optimization control.
Drawings
FIG. 1 is a flow chart of a method for compensating and optimizing a reconstruction error of a rotary cement kiln combustion field according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating the process of reconstructing a CFD combustion field of a rotary cement kiln based on a calcination mechanism according to an embodiment of the present invention;
FIG. 3 is a detailed flowchart of mining the internal relationship between the combustion efficiency of the rotary cement kiln and the operating variables and the factors of the combustion environment, and extracting the characteristic parameter data closely related to the combustion efficiency according to one embodiment of the present invention;
fig. 4 is a block diagram of a hardware structure of a system for compensating and optimizing a reconstruction error of a rotary cement kiln combustion field according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be further described with reference to the accompanying drawings. In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description of the present invention, and do not indicate or imply that the device or assembly referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Wherein the terms "first position" and "second position" are two different positions.
In some embodiments of the present invention, a method for compensating and optimizing a reconstruction error of a rotary cement kiln combustion field based on a combination of finite element modeling and data driving is provided, as shown in fig. 1, including the following steps:
step 1: and establishing a finite element model of the rotary cement kiln combustion field based on mechanism modeling.
Step 2: and acquiring temperature simulation data of the finite element model.
And step 3: the internal relation between the combustion efficiency of the rotary cement kiln and a plurality of factors of operation variables and combustion environment is excavated, and characteristic parameter data closely related to the combustion efficiency is extracted.
And 4, step 4: and constructing a reconstructed error compensation model, and solving the error problem existing between the CFD reconstructed combustion field and the actual combustion process by using the selected characteristic parameter data as the modeling parameters of the error compensation model.
And 5: and an online optimization algorithm is adopted to perform online optimization on the reconstructed error compensation model of the rotary cement kiln combustion field, and real-time correction is performed on simulation data by combining actual production data, so that the problem of timeliness of the reconstructed error compensation model is solved, and the modeling precision of the reconstructed error compensation model is improved.
Each step of the finite element modeling and data driving combined cement rotary kiln combustion field reconstruction error compensation and optimization method is described in detail below with reference to fig. 2 and 3.
Step 1: and carrying out real-time accurate acquisition on factory data.
And (3) establishing a finite element model of the rotary cement kiln combustion field by adopting finite element analysis software Ansys workbench 18.0. The finite element model reflects the real temperature field distribution condition in the rotary kiln as much as possible. The step of establishing the combustion field finite element model comprises the following steps:
step 21: and (4) accurately collecting the data of the cement production field. The system mainly comprises real-time data of a cement kiln system and laboratory test data, and the data can reflect the calcination condition in the kiln as comprehensively as possible.
Step 22: the abnormal data of the field data are eliminated and filtered, statistical tools such as Principal Component Analysis (PCA) are utilized for analysis, and different working conditions are divided according to the actual operation condition of the field.
Step 23: and (4) acquiring and analyzing process parameters. The method comprises the steps of determining a physical model of the rotary kiln, initial parameters and boundary conditions under multiple working conditions. Based on the specification and size of the rotary kiln of an actual cement production line, a physical model of the rotary kiln is determined according to the combustion range of coal dust in the kiln (the combustion of the coal dust in the rotary kiln is mainly carried out in a combustion zone within 20m near a combustor, so a calculation area is taken as 20m), grid division is carried out, and the measured parameters of the thermal calibration of the production line are taken as initial parameters for calculation. And analyzing the steady state values and the dynamic changes of the multiple working condition points, and determining the boundary conditions under each working condition.
Step 24: A2D partial differential equation is established for the furnace based on material conservation, energy conservation and momentum conservation, parameters such as temperature, gas components and material components are described, and a mathematical model required by CFD program calculation is selected, wherein the mathematical model mainly comprises a pulverized coal combustion mechanism model, a turbulence model and a radiation model. The coal powder combustion mechanism model is mainly divided into two stages of pyrolysis and coal tar burnout, and the derivation process of the pyrolysis model and the coal tar burnout model is as follows:
a) pyrolysis model:
when pulverized coal is injected into the rotary kiln from a burner, H2O contained in the coal is firstly released by heating, and volatile gases such as CO, CO2 and H2 are gradually released along with the increase of the temperature.
Figure BDA0002732738900000051
Figure BDA0002732738900000052
Wherein the reaction rate constant k1And k2Given by the Arrhenius formula:
Figure BDA0002732738900000053
Figure BDA0002732738900000054
wherein alpha is1,α2,E1,E2,A1,A2，R,TavIs an empirical constant.
b) Coal coke burnout model
The burning rate of the coal coke is as follows:
Figure BDA0002732738900000055
in the formula, ApRefers to the surface area of the particle, Pox is the partial pressure of oxygen around the particle, D0K is the chemical reaction rate constant, the diffusion coefficient of oxygen to the particle surface.
And the selection of the turbulence model takes the stability of calculation, time economy and the reliability of an application result into consideration, so that a standard readable k-epsilon model is selected and taken into consideration comprehensively.
The radiation model is a P1 radiation model, the radiation heat exchange and scattering effects between the particle phase and the gas phase can be reflected, and the method has the advantages of low calculation cost, short time consumption and the like.
Step 25: and (5) CFD modeling and simulation. And determining each parameter of numerical calculation according to the selected mathematical model and the boundary conditions under each working condition to carry out CFD modeling and simulation.
Step 26: and judging the convergence of the simulation result. Selecting residuals less than 10-6As a basis for convergence determination.
Step 2: and acquiring temperature simulation data of the finite element model.
Step 27: and (4) obtaining the distribution of the temperature field in the kiln through CFD finite element simulation, and displaying the result in two forms of an image and data. The images comprise a distribution cloud picture of the temperature field of the combustion flame in the kiln, a gas concentration field and a flow field cloud picture, and the calcining information of the material in the kiln can be visually obtained in the form of the images.
Step 28: the temperature simulation data is original data obtained by finite element modeling simulation of a rotary kiln combustion field and convergence judgment, and has a certain error with an actual combustion process.
And step 3: the internal relation between the combustion efficiency of the rotary cement kiln and a plurality of factors of operation variables and combustion environment is excavated, and characteristic parameter data closely related to the combustion efficiency is extracted. The selected modeling parameter data mainly comprises online real-time parameters, offline laboratory parameters and combustion field reconstruction information parameters:
step 31: a measurable variable associated with combustion state. Including online parameters and laboratory offline parameters. The main factors causing the reconstruction errors are analyzed and selected from the selected factors, and the key link for realizing error compensation is realized. Selecting a modeling parameter closely related to a reconstruction error based on mutual information and an extreme learning machine neural network research variable selection method; aiming at the problem of data dispersion, a variable matching method is researched based on a time series trend prediction method, and sample recombination is realized.
Step 32: the selected modeling parameter data mainly comprises online real-time parameters, offline laboratory parameters and combustion field reconstruction information parameters:
in combination with the above analysis, the on-line real-time parameters mainly include temperature parameters (outlet temperature of the decomposing furnace, secondary air temperature, burning zone temperature), quality parameters (raw material amount entering the kiln, coal feeding amount at the head and the tail of the kiln, clinker amount leaving the kiln), pressure parameters (outlet pressure of the decomposing furnace, coal feeding air pressure at the head of the kiln), flue gas composition parameters (carbon dioxide, oxygen, carbon monoxide, nitrogen) and other parameters (current of the main engine of the kiln). Preferably, the burning zone temperature is online temperature real-time data measured by performing feature extraction on combustion flame inside the rotary kiln through a Pyroscan infrared thermal imaging instrument.
The parameters of the off-line laboratory mainly comprise raw clinker component parameters (raw material three-rate value and clinker three-rate value), coal powder industrial analysis parameters (coal powder heat value and moisture), quality parameters (free calcium oxide) and other parameters (kiln tail raw material decomposition rate);
the combustion field reconstruction information parameters are mainly temperature simulation data of the kiln system obtained through CFD combustion field reconstruction.
The selected modeling parameter data processing mainly comprises abnormal value elimination and filtering, wherein the step of eliminating the abnormal values by the Lauda criterion comprises the following steps:
1) will change the variable xiThe average value of the N data is obtained;
2) calculating xiDeviation e of terms from the meani；
3) Calculating a standard deviation sigma;
4) when data xiDeviation e ofi(1. ltoreq. i. ltoreq.n) satisfies | eiIf | > 3 σ, x is determinediIf the abnormal value is found, the abnormal value is eliminated.
Wherein:
the variable xiThe average value formula of the N data is as follows:
Figure BDA0002732738900000071
the calculation xiDeviation e of terms from the meaniThe formula is as follows:
Figure BDA0002732738900000072
the formula for calculating the standard deviation sigma is as follows:
Figure BDA0002732738900000073
the mean filtering formula for processing the selected parameter data is as follows:
Figure BDA0002732738900000074
where m is the time window length of the mean filtering.
Step 33: and establishing a combustion field reconstruction error compensation model. After the selected modeling parameter data are processed, a cement rotary kiln combustion field reconstruction error compensation model is designed by adopting a fuzzy reasoning system and deep neural network based hybrid method. The input variables of the reconstructed error compensation model are linear real-time parameters and offline laboratory parameters, and the model output is the error of the temperature simulation data obtained by reconstructing the temperature of the in-kiln burning zone measured by the CCD camera and the CFD burning field.
Step 34: and acquiring a combustion field reconstruction error index variable through the established error compensation model. The prediction error of the method corrects the output of the combustion field reconstruction model, and the error relation between the CFD reconstruction combustion field and the actual combustion process is analyzed to obtain corrected temperature data.
Step 35: and (4) performing online optimization on the combustion field reconstruction error compensation model established in the step (4) by adopting a rolling optimization idea, solving the problem that the combustion field reconstruction error fluctuates along with the change of the working condition, ensuring the timeliness of the error compensation model, enabling the model output to compensate the combustion field reconstruction error in real time along with the change of the working condition, and performing model verification by utilizing the real-time data of the rotary cement kiln.
The invention also provides a storage medium which can be read and written by a computer, wherein the storage medium stores program instructions, and the computer reads the program information and then executes the reconstruction error compensation and optimization method of the rotary cement kiln combustion field according to any scheme.
Some embodiments of the present invention further provide a system for compensating and optimizing a reconstruction error of a rotary cement kiln combustion field, as shown in fig. 4, where the system includes: at least one processor 401 and at least one memory 402, wherein at least one memory 402 stores program information, and after the at least one processor 401 reads the program information, the method for compensating and optimizing the reconstruction error of the combustion field of the rotary cement kiln is executed. The apparatus may further comprise: an input device 403 and an output device 404. The processor 401, the memory 402, the input device 403 and the output device 404 may be connected by a bus or other means, and fig. 4 illustrates an example of a connection by a bus.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A method for compensating and optimizing the reconstruction error of a rotary cement kiln combustion field is characterized by comprising the following steps:
step 1: establishing a finite element model of a cement rotary kiln combustion field;
step 2: acquiring temperature simulation data of the finite element model; the temperature simulation data is original data obtained by performing finite element modeling simulation on the rotary kiln combustion field and performing convergence judgment;
and step 3: acquiring internal relation among the combustion efficiency of the rotary cement kiln, operation variables and a combustion environment, and extracting characteristic parameter data related to the combustion efficiency; the characteristic quantity data comprises online real-time parameters, offline laboratory parameters and combustion field reconstruction information parameters;
and 4, step 4: using the selected characteristic parameter data as a modeling parameter of the error compensation model; designing a cement rotary kiln combustion field reconstruction error compensation model based on a fuzzy inference system and a deep neural network mixing method, and analyzing an error relation between a CFD reconstruction combustion field and an actual combustion process;
and 5: performing online optimization on the cement rotary kiln combustion field reconstruction error compensation model by adopting an online optimization algorithm, and correcting simulation data in real time by combining actual production data; and (4) performing online optimization on the combustion field reconstruction error compensation model established in the step (4) by adopting a rolling optimization idea, so that the output of the model compensates the combustion field reconstruction error in real time along with the change of the working condition, and performing model verification by using the real-time data of the rotary cement kiln.
2. The rotary cement kiln combustion field reconstruction error compensation and optimization method according to claim 1, wherein the step 1 comprises:
1.1: selecting a mathematical model, wherein the mathematical model comprises a pulverized coal combustion mechanism model, a turbulence model and a radiation model;
1.2: acquiring and analyzing process parameters, wherein the process parameters comprise the size of a rotary cement kiln, initial parameters and boundary conditions; determining a physical model of the rotary kiln of an actual cement production line according to the combustion range of pulverized coal in the rotary kiln and carrying out grid division on the basis of the specification and the size of the rotary kiln of the actual cement production line, and calculating by taking thermotechnical calibration actual measurement parameters of the production line as initial parameters;
1.3: data acquisition and pretreatment, including real-time data acquisition of a cement kiln system and laboratory test data acquisition, wherein the data are used for reflecting the calcination condition in the kiln, and different working conditions are divided according to the actual field operation condition; determining boundary conditions under each working condition according to the steady state values and the dynamic changes of the multiple working condition points;
1.4: based on CFD combustion field reconstruction, determining each parameter of numerical calculation according to the selected mathematical model and the boundary conditions under each working condition to carry out CFD modeling and simulation; judging the convergence of the simulation calculation result of the CFD program, and selecting the residual error to be less than 10-6As a basis for convergence determination.
3. The rotary cement kiln combustion field reconstruction error compensation and optimization method according to claim 2, wherein in the step 1, the derivation process of the pulverized coal combustion mechanism model is divided into two stages, namely pyrolysis and coal tar burnout, wherein:
pyrolysis model:
when the pulverized coal is sprayed into the rotary kiln from the burner, H2O contained in the coal is firstly released, and volatile gas is gradually released along with the rise of the temperature;
Figure FDA0002732738890000021
Figure FDA0002732738890000022
in the formula (II), the reaction rateConstant k1And k2Given by the following equation:
Figure FDA0002732738890000023
Figure FDA0002732738890000024
wherein alpha is1,α2,E1,E2,A1,A2，R，TavIs an empirical constant;
coal char burnout model:
the burning rate of the coal coke is as follows:
Figure FDA0002732738890000025
in the formula, ApRefers to the surface area of the particle, Pox is the partial pressure of oxygen surrounding the particle, D0 is the diffusion coefficient of oxygen to the surface of the particle, k is the chemical reaction rate constant, mpThe amount of the coke is determined.
4. The rotary cement kiln combustion field reconstruction error compensation and optimization method according to claim 2, characterized in that:
in the step 1, a standard readable k-epsilon model is selected as a turbulence model.
5. The rotary cement kiln combustion field reconstruction error compensation and optimization method according to claim 2, characterized in that:
in the step 1, the radiation model is selected from a P1 radiation model.
6. The rotary cement kiln combustion field reconstruction error compensation and optimization method according to any one of claims 1 to 5, characterized in that in step 3:
the online real-time parameters include:
temperature parameters including the outlet temperature of the decomposing furnace, secondary air temperature and the temperature of a burning zone; the burning zone temperature is online temperature real-time data measured by performing feature extraction on combustion flame inside the rotary kiln through a CCD camera;
the quality parameters comprise the raw material amount entering the kiln, the coal feeding amount at the head and the tail of the kiln and the clinker amount after the kiln is taken out;
pressure parameters including outlet pressure of the decomposing furnace and blast pressure of kiln head coal feeding air;
flue gas composition parameters including carbon dioxide, oxygen, carbon monoxide and nitrogen;
other parameters, including kiln host current;
the offline laboratory parameters include:
raw clinker ingredient parameters including raw material three-rate values and clinker three-rate values;
coal powder industrial analysis parameters including coal powder heat value and moisture;
quality parameters including free calcium oxide;
the combustion field reconstruction information parameters are the temperature simulation data of the kiln system obtained through CFD combustion field reconstruction.
7. The rotary cement kiln combustion field reconstruction error compensation and optimization method according to claim 6, wherein the step 3 comprises:
and removing abnormal values of the selected characteristic parameter data according to a Lauda criterion, and then carrying out mean value filtering processing on the characteristic parameter data after the abnormal values are removed.
8. The rotary cement kiln combustion field reconstruction error compensation and optimization method according to claim 7, characterized in that:
the step of rejecting abnormal values by Lauda criterion comprises the following steps:
n characteristic parameter data xiAnd (3) calculating an average value:
Figure FDA0002732738890000041
calculating xiDeviation e of terms from the meani：
Figure FDA0002732738890000042
Calculating the standard deviation σ:
Figure FDA0002732738890000043
when the characteristic parameter data xiDeviation e ofiSatisfy | eiIf | > 3 σ, x is determinediRemoving abnormal values;
wherein, the mean value filtering formula for processing the selected parameter data is as follows:
Figure FDA0002732738890000044
where m is the time window length of the mean filtering.
9. A storage medium, wherein the storage medium stores program information, and a computer reads the program information and executes the reconstruction error compensation and optimization method for the rotary cement kiln combustion field according to any one of claims 1 to 8.
10. A system for compensating and optimizing the reconstruction error of a rotary cement kiln combustion field is characterized by comprising:
at least one processor and at least one memory, wherein at least one memory stores program information, and the at least one processor executes the cement rotary kiln combustion field reconstruction error compensation and optimization method according to any one of claims 1 to 8 after reading the program information.
CN202011123190.8A 2020-10-20 2020-10-20 Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system Active CN112380738B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011123190.8A CN112380738B (en) 2020-10-20 2020-10-20 Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011123190.8A CN112380738B (en) 2020-10-20 2020-10-20 Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system

Publications (2)

Publication Number Publication Date
CN112380738A true CN112380738A (en) 2021-02-19
CN112380738B CN112380738B (en) 2022-10-14

Family

ID=74580238

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011123190.8A Active CN112380738B (en) 2020-10-20 2020-10-20 Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system

Country Status (1)

Country Link
CN (1) CN112380738B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
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
CN113657484A (en) * 2021-08-13 2021-11-16 济南大学 Method for dividing and identifying typical working conditions of cement grate cooler
CN116625827A (en) * 2023-06-17 2023-08-22 广州市盛通建设工程质量检测有限公司 Method, device, equipment and medium for testing compression resistance of concrete containing steel slag fine aggregate

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102629104A (en) * 2011-12-01 2012-08-08 燕山大学 Calcination predictive control system and method for rotary cement kiln
CN104794263A (en) * 2015-03-31 2015-07-22 济南大学 Hybrid modeling method for rotary cement kiln burning zone temperature based on LS_SVM soft measurement
CN111665809A (en) * 2020-06-16 2020-09-15 济南大学 Modeling method and system for segmentation mechanism of rotary cement kiln

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102629104A (en) * 2011-12-01 2012-08-08 燕山大学 Calcination predictive control system and method for rotary cement kiln
CN104794263A (en) * 2015-03-31 2015-07-22 济南大学 Hybrid modeling method for rotary cement kiln burning zone temperature based on LS_SVM soft measurement
CN111665809A (en) * 2020-06-16 2020-09-15 济南大学 Modeling method and system for segmentation mechanism of rotary cement kiln

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
DONGMEIFU等: "Research on Soft Measurement Method of Temperature Field in Cement Rotary Kiln", 《PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE》 *
周武洲: "基于集成优化算法的水泥熟料游离氧化钙预测研究", 《万方数据知识服务平台》 *
石忠强: "陶粒回转窑烧成工艺的数值模拟及相关技术研究", 《万方数据知识服务平台》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN113657484A (en) * 2021-08-13 2021-11-16 济南大学 Method for dividing and identifying typical working conditions of cement grate cooler
CN113657484B (en) * 2021-08-13 2024-02-09 济南大学 Method for dividing and identifying typical working conditions of cement grate cooler
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
CN116625827A (en) * 2023-06-17 2023-08-22 广州市盛通建设工程质量检测有限公司 Method, device, equipment and medium for testing compression resistance of concrete containing steel slag fine aggregate
CN116625827B (en) * 2023-06-17 2024-01-23 广州市盛通建设工程质量检测有限公司 Method, device, equipment and medium for testing compression resistance of concrete containing steel slag fine aggregate

Also Published As

Publication number Publication date
CN112380738B (en) 2022-10-14

Similar Documents

Publication Publication Date Title
CN112380738B (en) Rotary cement kiln combustion field reconstruction error compensation and optimization method, storage medium and system
CN109508818B (en) Online NOx prediction method based on LSSVM
CN110807577A (en) Pollution emission prediction method and device
CN110189800B (en) Furnace oxygen content soft measurement modeling method based on multi-granularity cascade cyclic neural network
CN108647481A (en) A kind of rotary kiln burning zone temperature flexible measurement method
Wu et al. Integrated soft sensing of coke-oven temperature
CN112784474A (en) Boiler coal-fired relative heat value calculation method based on unit coal powder oxygen consumption
CN110569567B (en) Method and system for measuring temperature of coke oven flue
CN114036758B (en) Boiler combustion state dynamic display method based on numerical simulation and machine learning
CN113515043A (en) Method for calculating dry quenching loss rate in real time based on BP neural network
CN117331384A (en) Coke oven temperature control method, system, equipment and storage medium
CN111505236A (en) Coal quality monitoring method for acquiring element analysis in real time based on coal quality industrial analysis
Bazhanov et al. Development of control system for a complex technological object using fuzzy behavior charts
CN113836794B (en) Soft and hard combined fly ash carbon content online monitoring method
CN112949054B (en) Soft measurement method and system for heat value of coal entering coal of coal-fired boiler
CN115935784A (en) Method and system for analyzing fuel data in combustion system of architectural ceramic kiln
CN114267418A (en) Real-time measurement method and device for boiler operation data
CN109632881B (en) Metallurgical gas calorific value soft measurement method based on gas preheating system heat exchange parameters
CN114971258A (en) Industrial process optimization method and system based on coke quality prediction
CN206328336U (en) The system of nitrogen oxides in a kind of coke oven exhaust gas from Sources controlling
CN116189805B (en) Coal quality change monitoring method based on oxygen prediction
Jin et al. Data Mining for Complex Thermal System Modeling
CN116879513B (en) Verification method, device, equipment and storage medium of gas analysis system
Song et al. Neural Network-based Modeling or Boiler Combustion Control System for Power Generation
CN115639339B (en) Online coal quality analysis method for coal yard

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