CN116525014A - Volatilizing kiln temperature field prediction method based on thermodynamic mechanism and infrared image data fusion - Google Patents
Volatilizing kiln temperature field prediction method based on thermodynamic mechanism and infrared image data fusion Download PDFInfo
- Publication number
- CN116525014A CN116525014A CN202310438344.XA CN202310438344A CN116525014A CN 116525014 A CN116525014 A CN 116525014A CN 202310438344 A CN202310438344 A CN 202310438344A CN 116525014 A CN116525014 A CN 116525014A
- Authority
- CN
- China
- Prior art keywords
- temperature
- kiln
- thermodynamic
- infrared image
- model
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000004927 fusion Effects 0.000 title claims abstract description 41
- 239000011343 solid material Substances 0.000 claims abstract description 27
- 238000005457 optimization Methods 0.000 claims abstract description 26
- 238000006243 chemical reaction Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000006276 transfer reaction Methods 0.000 claims abstract description 4
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 17
- 239000003546 flue gas Substances 0.000 claims description 17
- 238000012546 transfer Methods 0.000 claims description 17
- 239000000463 material Substances 0.000 claims description 14
- 230000005855 radiation Effects 0.000 claims description 14
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 230000004323 axial length Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000001931 thermography Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- XLOMVQKBTHCTTD-UHFFFAOYSA-N Zinc monoxide Chemical compound [Zn]=O XLOMVQKBTHCTTD-UHFFFAOYSA-N 0.000 description 24
- 239000011787 zinc oxide Substances 0.000 description 12
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 9
- 239000011701 zinc Substances 0.000 description 9
- 229910052725 zinc Inorganic materials 0.000 description 9
- 239000000571 coke Substances 0.000 description 6
- 239000000203 mixture Substances 0.000 description 6
- 239000000428 dust Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000003723 Smelting Methods 0.000 description 3
- 229910052799 carbon Inorganic materials 0.000 description 3
- 239000003638 chemical reducing agent Substances 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 239000002893 slag Substances 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006479 redox reaction Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000002386 leaching Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/20—Recycling
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Crystallography & Structural Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention relates to the technical field of prediction of a temperature field of a volatilizing kiln, and particularly discloses a method for predicting the temperature field of the volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data, which comprises the following steps: step S1, a thermodynamic model is established according to the heat transfer and chemical reaction process of the volatilizing kiln, and a predicted temperature is obtained according to the thermodynamic model; s2, acquiring an infrared image of a kiln head area of the volatilizing kiln, processing the infrared image and extracting the actual solid material temperature; s3, constructing a parameter optimization model by minimizing an error between a predicted temperature obtained by the thermodynamic model and an actual solid material temperature; s4, determining a model parameter value to be optimized, and obtaining a parameter optimization result; and S5, substituting the parameter optimization result into a thermodynamic model to obtain a fusion model, and obtaining a prediction result of the temperature field of the volatilizing kiln through the fusion model so as to solve the problem that the temperature field of the volatilizing kiln is difficult to accurately predict in the prior art.
Description
Technical Field
The application relates to the technical field of prediction of a temperature field of a volatilizing kiln, and particularly discloses a method for predicting the temperature field of the volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data.
Background
The rotary volatilizing kiln for zinc oxide is a core equipment for recovering zinc oxide dust by treating zinc leached slag, and is characterized by that it uses the mixture formed from leached slag and coke as raw material, and makes them produce a series of complex oxidation-reduction reactions under the condition of high-temperature reaction, then separates zinc-containing oxide from the mixture. The axial length of the volatilizing kiln exceeds 60 m, the inner diameter exceeds 4 m, and the internal temperature field is the most important factor affecting the technical index. However, because of the complex chemical mechanism of the volatilizing kiln, the large reaction size, the closed interior space and the 360 degree rotation, real-time measurement of the complete temperature field is almost impossible. In the actual industrial process, workers can only infer the temperature distribution in the kiln by observing the appearance and the form of the kiln head flame image through experience, so as to control the temperature field. Because this control method lacks complete temperature field data as an operational guide, workers can only guarantee product quality at the expense of excessive coke consumption.
Most of the existing industrial rotary kiln temperature field prediction methods are based on basic principles such as mass conservation and energy conservation, and a pure thermodynamic model is established to realize temperature field prediction. For common industrial rotary kilns such as cement and alumina, the fuel only provides heat for high-temperature reaction and hardly causes chemical reaction. However, the coke in the volatilizing kiln not only provides heat as a combustion agent, but also participates in the chemical reaction as a reducing agent. Compared with other industrial kilns, the thermodynamic model is more complicated due to the complex chemical reaction behavior of carbon elements in the volatilizing kiln. In addition, the thermodynamic parameters of other rotary kilns can be significantly mismatched in the thermodynamic model of the volatilizing kiln. Because of the unique reaction mechanism of the volatilizing kiln, it is difficult to accurately predict the temperature field by a method relying only on pure thermodynamic modeling.
Accordingly, the inventors have provided a method for predicting a temperature field of a volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data, so as to solve the above-mentioned problems.
Disclosure of Invention
The invention aims to solve the problem that the temperature field of a zinc oxide rotary volatilizing kiln is difficult to accurately predict in the prior art.
In order to achieve the above purpose, the basic scheme of the invention provides a volatilizing kiln temperature field prediction method based on fusion of a thermodynamic mechanism and infrared image data, which comprises the following steps:
step S1, establishing a thermodynamic model related to chemical reaction heat according to heat transfer and chemical reaction processes of a volatilizing kiln, and obtaining a predicted temperature according to the thermodynamic model;
s2, acquiring an infrared image of a kiln head area of the volatilizing kiln, processing the infrared image and extracting the actual solid material temperature;
s3, constructing a parameter optimization model by minimizing an error between a predicted temperature obtained by the thermodynamic model and an actual solid material temperature;
s4, determining a model parameter value to be optimized by utilizing an optimization algorithm, and obtaining a parameter optimization result;
and S5, substituting the parameter optimization result into a thermodynamic model to obtain a fusion model, and obtaining a prediction result of the temperature field of the volatilizing kiln through the fusion model.
Further, the thermodynamic model is represented as follows:
Q sh-a ＝Q g-ew +Q ew-es +Q cs-cw
wherein,,
Q g-∈s indicating heat transfer between flue gas and exposed solid material, including convection termsAnd radiating item->
Q g-ew Representing heat transfer between flue gas and exposed kiln walls, including thermal convection termsAnd heat radiation item->
Q ew-es Indicating heat transfer between the exposed kiln wall and the exposed material, including heat radiation items
Q cw-cs Representing heat transfer between the covered inner wall and the covered material, including heat radiation itemsAnd heat conduction item->
Q sh-a Representing heat transfer of the enclosure to the external environment, including thermal convection termsAnd heat radiation item->
F. C and T are mass flow, specific heat capacity and temperature, respectively;
subscripts s and g represent solid material and flue gas, respectively.
Further, in the step S2, the step of processing the image is as follows:
s2.1, an infrared thermal imaging system is built to acquire an infrared image of a kiln head area of the volatilizing kiln in real time;
s2.2, preprocessing an infrared image by utilizing mathematical morphology operation, and extracting the background and the foreground of the image;
step S2.3, acquiring the position of invalid information in the image based on a target detection algorithm of YOLOv 5S;
and step S2.4, fusing the image processing results in the steps S2.2 and 2.3 to obtain a temperature pseudo-color image of the solid material.
Further, the specific formula for preprocessing the infrared image by using mathematical morphology operation is as follows:
I 22 (m,n)＝I 21 (m,n)○B
I 23 (m,n)＝I 22 (m,n)●B
I 24 (m,n)＝Bwareaopen(I 23 (m,n))
wherein,,
I 1 (m, n) is an original temperature pseudo-color image, and each pixel coordinate (m, n) corresponds to a temperature value;
ostu's represents an Ojin dynamic threshold segmentation method;
b is a structural element for performing mathematical morphological operations on the image;
the O and the ∈are respectively an open operation and a closed operation;
bwaseaopen is a function used to delete small area objects.
Further, in the step S3, a general thermodynamic parameter is determined by minimizing an error between the predicted temperature and the true temperature.
Further, in the step S3, the thermal conductivity of the material and the flue gas and the emissivity of the material, the flue gas and the kiln wall are used as general thermodynamic parameters.
Further, the parametric optimization model formula is expressed as follows:
wherein N is 1 Is the sample size of the training set;
N 2 is the number of temperature points of the solid material;
N 3 is the number of effective temperature points in the infrared image;
d represents depth information of the kiln head region;
l is the axial length of the kiln body;
T s (x)the predicted temperature of the thermodynamic model solved at the axial position x;
Y t the temperature of the real solid material is extracted from the infrared image processing result;
the predicted solid fluidized bed temperature is related to the unknown thermodynamic parameter theta u.t And unknown system parameter θ u.s Is a function of (2);
lower and upper represent the upper and lower limits, respectively, of the optimized parameter.
Further, in the step S4, the flow rate, the kinematic viscosity and the density of the flue gas are used as model parameters to be optimized.
The principle and effect of this scheme lie in:
1. aiming at the problems that the chemical mechanism of the volatilizing kiln is complex, the reaction size is large, the internal space is airtight, and the temperature field caused by 360-degree rotation is difficult to measure in real time, the invention provides the rotary volatilizing kiln temperature field prediction method based on the fusion of thermodynamics and infrared images, accurately and effectively realizes the soft measurement of the complete temperature field, and provides operation guidance information for optimizing the low-carbon operation of the zinc smelting volatilizing kiln.
2. The optimal general thermodynamic parameters are determined in advance, and the number of unknown parameters needing to be optimized is greatly reduced. And the pure thermodynamic model has poor local optimal solution due to too many unknown parameters, so that the model is difficult to quickly converge to a satisfactory solution. Compared with a temperature field prediction method based on pure thermodynamics, the method has more excellent prediction performance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a process flow diagram of a zinc oxide rotary volatilizing kiln;
FIG. 2 shows a frame diagram of a method for predicting a temperature field of a volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data according to an embodiment of the present application;
FIG. 3 shows an original temperature pseudo-color image in a method for predicting a temperature field of a volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data according to an embodiment of the present application;
fig. 4 shows an image after mathematical morphology operation in a method for predicting a temperature field of a volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data according to an embodiment of the present application;
fig. 5 shows an image of a target detection result based on YOLOv5s in a method for predicting a temperature field of a volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data according to an embodiment of the present application;
FIG. 6 shows a pseudo-color temperature image of a solid material in a method for predicting a temperature field of a volatilizing kiln based on fusion of a thermodynamic mechanism and infrared image data according to an embodiment of the present application;
fig. 7 shows a comparison of temperature field predictions for a pure thermodynamic model versus a fusion model.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention for achieving the intended purpose, the following detailed description will refer to the specific implementation, structure, characteristics and effects according to the present invention with reference to the accompanying drawings and preferred embodiments.
A prediction method of a volatilizing kiln temperature field based on fusion of a thermodynamic mechanism and infrared image data takes a zinc oxide rotary volatilizing kiln of a zinc smelting plant as an example, the process flow is shown in a figure 1, a mixture consisting of zinc leaching slag and coke is subjected to a series of complex oxidation-reduction reactions under a high-temperature reaction, and then zinc oxide is separated from the mixture. Volatilizing kilns differ from other rotary kilns in that their coke is used not only as a fuel, but also as an important reductant for reducing zinc. When the kiln body rotates, the solid material moves from the kiln tail region to the kiln head region. Simultaneously, the gas moves from the kiln head area to the kiln tail area under negative pressure. The solid material enters a high-temperature reaction zone after the drying and preheating processes. Zinc oxide dust generated in the volatilization process is collected in a dust settling chamber. Unreacted solid material is discharged from the kiln head region.
As shown in fig. 2, the prediction of the temperature field of the zinc oxide rotary volatilizing kiln mainly comprises four parts: thermodynamic model construction, infrared image processing, parameter optimization and temperature field prediction, and the method specifically comprises the following steps:
step S1: on the basis of carefully analyzing the heat transfer and chemical reaction process of the volatilizing kiln, a thermodynamic model involving the heat of chemical reaction is established, specifically as follows:
step S1.1: the following reaction equations show the core chemistry involved in the temperature field prediction method. Part of the coke is used as fuel agent to provide heat, and the other part is used as reducing agent and ZnFe 2 O 4 Reacts with ZnO to form zinc vapour. Zinc oxide is first reduced to zinc vapor and then reacted with oxygen to produce zinc oxide dust.
C+O 2 ＝CO 2
3ZnFe 2 O 4 +4C+2O 2 ＝2Fe 3 O 4 +3Zn+4CO 2
2ZnO+2C+O 2 ＝2Zn(g)+2CO 2
2Zn(g)+O 2 ＝2ZnO
Step S1.2: the heat of chemical reaction is part of the thermal composition in the thermodynamic model, which is related to the rate of change and enthalpy of the components, and can be expressed as:
Q chem，g ＝Σr 1 (x)ΔH 1
Q chem，s ＝∑r 1 (x)ΔH i ，i＝2,3
wherein Q is chem，g ，Q chem，s Respectively represent the chemical reaction heat of the smoke and the materials, r 1 ，r 2 ，r 3 Respectively C, znFe 2 O 4 And the component change rate of ZnO, Δh represents the corresponding enthalpy.
Step S1.3: heat transfer is another part of the thermal composition in the thermodynamic model, mainly comprising heat convection, heat radiation and heat conduction. Based on the law of conservation of energy, the thermodynamic model for temperature field prediction is represented as follows:
Q sh-a ＝Q g-ew +Q ew-es +Q cs-cw
wherein Q is g-∈s Indicating heat transfer between flue gas and exposed solid material, including convection termsAnd radiation itemQ g-ew Indicating the heat transfer between flue gas and exposed kiln walls, including the thermal convection term +.>And heat radiation item->Q ew-es Indicating the heat transfer between the exposed kiln wall and the exposed material, comprising only the heat radiation item +.>Q cw-cs Indicating the heat transfer between the covered inner wall and the covered material, comprising a heat radiation item +.>And heat conduction item->Q sh-a Indicating the heat transfer of the housing from the external environment,comprising thermal convection items->And heat radiation item->F. C and T are mass flow, specific heat capacity and temperature, respectively. Subscripts s and g represent solid material and flue gas, respectively.
Step S2: the infrared thermal imaging system is utilized to acquire an infrared image of the kiln head area of the volatilizing kiln in real time, and on the basis, the real and accurate solid material temperature is extracted by an image processing method, wherein the infrared image processing comprises the following steps:
step S2.1: an infrared thermal imaging system is built, and the system can acquire infrared images in real time;
step S2.2: the infrared image is preprocessed by mathematical morphological operation, so that the background and the foreground of the image are extracted, and the specific formula is as follows:
I 22 (m,n)＝I 21 (m,n)○B
I 23 (m,n)＝I 22 (M,n)●B
I 24 (m,n)＝Bwareaopen(I 23 (m,n))
wherein I is 1 (m, n) is an original temperature pseudo-color image, and each pixel coordinate (m, n) corresponds to a temperature value. Ostu's represents the method of dynamic threshold segmentation of Ojin. B is a structural element for performing mathematical morphological operations on the image. The o and ∈ are open and closed operations, respectively, and bwaseaopen is a function for deleting small-area objects. I 24 (m, n) is a divided image composed of a background and a foreground, and values corresponding to pixel positions where the foreground and the background are located are taken as 1 and 0, respectively.
Step S2.3: acquiring the position of invalid information in the image based on a target detection algorithm of YOLOv5 s;
step S2.4: and (3) fusing the image processing results in the steps S2.2 and 2.3 to obtain a temperature pseudo-color image of the solid material, wherein the specific formula is as follows:
I 4 (m,n)＝I 1 (m,n)*I 24 (m,n)*I 3 (m,n)
wherein I is 4 Is a temperature pseudo-color image of a solid material. I 3 Based on the image processing result obtained by YOLOv5s, the value of the pixel position where the image invalid information is located is 0, and the other positions are 1.
The present example selects representative images to illustrate the effectiveness of the proposed method, I 1 (m, n) represents an original temperature pseudo-color image, which is shown in fig. 3. I 24 (m, n) is I 1 The result obtained by mathematical morphological operations of (m, n) is shown in fig. 4, and consists of a background and a foreground. I 3 Is an image processing result based on YOLOv5s, as shown in fig. 5. The temperature pseudo-color image I of the solid material is obtained by fusing the results obtained after the image processing in the steps S2.2 and 2.3 4 The results are shown in fig. 6.
Step S3: a parameter optimization model is established, and the universal thermodynamic parameters applicable to any volatilizing kiln are extracted by minimizing the error between the predicted temperature and the actual temperature. The predicted temperature in the model is calculated by a thermodynamic model, and the real temperature is extracted by an infrared image processing method; the specific formula is as follows:
wherein N is 1 Is the sample size of the training set, N 2 Is the number of temperature points of the solid material, N 3 Is the effective number of temperature points in the infrared image. d is used to represent depth information of the kiln head region, and L is the axial length of the kiln body. T (T) s (x) Is a thermodynamic model inThe predicted temperature for the axial position x solution. Y is Y t Is the temperature of the real solid material extracted from the infrared image processing result.For predicted solid fluidized bed temperature, it is related to unknown thermodynamic parameter θ u.t And unknown system parameter θ u.s Is a function of (2). lower and upper represent the upper and lower limits, respectively, of the optimized parameter.
For the parameter optimization model described in step S3, the present embodiment collects 200 pieces of data in total in an actual industrial process, where the first 150 pieces are used to optimize unknown parameters in the thermodynamic model, and the last 50 pieces of data are used to test the accuracy of the parameter optimization model. The results after parameter optimization are shown in Table 1, where λ s And lambda (lambda) g Respectively show the heat conductivity, epsilon of the material and the smoke s 、ε w And epsilon g The emissivity of the material, the flue gas and the kiln wall are shown respectively, and the extracted general thermodynamic parameters are applicable to all volatilizing kilns. v g 、u g And ρ g Respectively, the flow rate, the kinematic viscosity and the density of the flue gas, which parameters can be changed with the production process conditions in different volatilizing kilns.
Table 1: optimization results of unknown parameters in thermodynamic models
Step S4: the general thermodynamic parameters extracted in step S3 are applied to another volatilizing kiln having a different physical size, and the volatilizing kiln in step S4 has the same heat transfer mechanism, although it has a different physical size, than the volatilizing kiln in step S3. In order to determine unknown parameters to be optimized based on a temperature field prediction method (pure thermodynamic model) of pure thermodynamics and a temperature field prediction method (fusion model) of thermodynamic mechanism and infrared image fusion, a comparative experiment of the two models is designed to show the effect of the invention, and the method is specifically as follows:
step S4.1: for a pure thermodynamic model, since the general thermodynamic parameters are not determined in advance, the total number of parameters that need to be optimized is 8, in particular λ s ，λ g ，ε s ，ε w ，ε g ，v g ，u g ，ρ g ；
Step S4.2: for the fusion model, since the general thermodynamic parameters are determined in advance using the infrared image processing method, it is specifically shown in table 1. Therefore, the total number of parameters to be optimized of the fusion model is only 3, in particular v g ，u g ，ρ g ；
Step S4.3: model parameters to be optimized in the two models are identified by using an optimization algorithm, and the optimization results are shown in table 2.
Table 2: parameter optimization result of temperature field prediction model
Step S5: substituting the parameter optimization result into a thermodynamic model to obtain a fusion model, wherein the fusion model is based on the thermodynamic model, unknown parameters in the thermodynamic model are determined in advance through the parameter optimization model, the thermodynamic model is the fusion model after parameter optimization, and the prediction result of the temperature field of the volatilizing kiln can be obtained through the fusion model, so that accurate prediction of the temperature field of the volatilizing kiln is realized.
In this embodiment, the parameter optimization results in table 2 are substituted into the thermodynamic model, so as to obtain the temperature field prediction results of the pure thermodynamic model and the fusion model, as shown in fig. 7. Correspondingly, table 3 shows that the fusion model of the present embodiment has smaller MSE and MARE compared to the pure thermodynamic model, which means that the fusion model has better temperature field prediction accuracy.
Table 3: temperature field prediction result
Where MSE represents mean square error, MARE represents average absolute value of relative error, and the specific calculation formula is as follows:
where n represents the number of samples, y i Andrepresenting the true value and the predicted value of the i-th sample, respectively.
From the above results, compared with the temperature field prediction method based on pure thermodynamics, the method has more excellent prediction performance, because the optimal general thermodynamic parameters of the fusion model are determined in advance, and the number of unknown parameters needing to be optimized is greatly reduced. And the pure thermodynamic model has poor local optimal solution due to too many unknown parameters, so that the model is difficult to quickly converge to a satisfactory solution.
Aiming at the problems that the chemical mechanism of the volatilizing kiln is complex, the reaction size is large, the internal space is airtight, and the temperature field caused by 360-degree rotation is difficult to measure in real time, the invention provides the rotary volatilizing kiln temperature field prediction method based on the fusion of thermodynamics and infrared images, accurately and effectively realizes the soft measurement of the complete temperature field, and provides operation guidance information for optimizing the low-carbon operation of the zinc smelting volatilizing kiln.
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (8)
1. A volatilizing kiln temperature field prediction method based on thermodynamic mechanism and infrared image data fusion is characterized by comprising the following steps:
step S1, establishing a thermodynamic model related to chemical reaction heat according to heat transfer and chemical reaction processes of a volatilizing kiln, and obtaining a predicted temperature according to the thermodynamic model;
s2, acquiring an infrared image of a kiln head area of the volatilizing kiln, processing the infrared image and extracting the actual solid material temperature;
s3, constructing a parameter optimization model by minimizing an error between a predicted temperature obtained by the thermodynamic model and an actual solid material temperature;
s4, determining a model parameter value to be optimized by utilizing an optimization algorithm, and obtaining a parameter optimization result;
and S5, substituting the parameter optimization result into a thermodynamic model to obtain a fusion model, and obtaining a prediction result of the temperature field of the volatilizing kiln through the fusion model.
2. The method for predicting the temperature field of a volatilizing kiln based on fusion of thermodynamic mechanism and infrared image data according to claim 1, wherein the thermodynamic model is represented as follows:
Q sh-a ＝Q g-ew +Q ew-es +Q cs-cw
wherein,,
Q g-∈s indicating heat transfer between flue gas and exposed solid material, including convection termsAnd radiating item->
Q g-ew Representing heat transfer between flue gas and exposed kiln walls, including thermal convection termsAnd heat radiation item->
Q ew-es Indicating heat transfer between the exposed kiln wall and the exposed material, including heat radiation items
Q cw-cs Representing heat transfer between the covered inner wall and the covered material, including heat radiation itemsAnd heat conduction item
Q sh-a Representing heat transfer of the enclosure to the external environment, including thermal convection termsAnd heat radiation item->
F. C and T are mass flow, specific heat capacity and temperature, respectively;
subscripts s and g represent solid material and flue gas, respectively.
3. The method for predicting the temperature field of the volatilizing kiln based on the fusion of the thermodynamic mechanism and the infrared image data according to claim 1, wherein in the step S2, the step of processing the image is as follows:
s2.1, an infrared thermal imaging system is built to acquire an infrared image of a kiln head area of the volatilizing kiln in real time;
s2.2, preprocessing an infrared image by utilizing mathematical morphology operation, and extracting the background and the foreground of the image;
step S2.3, acquiring the position of invalid information in the image based on a target detection algorithm of YOLOv 5S;
and step S2.4, fusing the image processing results in the steps S2.2 and 2.3 to obtain a temperature pseudo-color image of the solid material.
4. The method for predicting the temperature field of the volatilizing kiln based on the fusion of the thermodynamic mechanism and the infrared image data according to claim 3, wherein the specific formula for preprocessing the infrared image by using mathematical morphology operation is as follows:
I 22 (m，n)＝I 21 (m，n)οB
I 23 (m，n)＝I 22 (m，n)·B
I 24 (m，n)＝Bwareaopen(I 23 (m，n))
wherein,,
I 1 (m, n) is an original temperature pseudo-color image, and each pixel coordinate (m, n) corresponds to a temperature value;
ostu's represents an Ojin dynamic threshold segmentation method;
b is a structural element for performing mathematical morphological operations on the image;
the omic sum is an open operation and a closed operation respectively;
bwaseaopen is a function used to delete small area objects.
5. The method for predicting the temperature field of a volatilizing kiln based on fusion of thermodynamic mechanism and infrared image data according to claim 1, wherein in the step S3, the universal thermodynamic parameter is determined by minimizing the error between the predicted temperature and the true temperature.
6. The method for predicting the temperature field of the volatilizing kiln based on the fusion of the thermodynamic mechanism and the infrared image data according to claim 5, wherein in the step S3, the thermal conductivity of materials and flue gas and the emissivity of the materials, the flue gas and the kiln wall are used as general thermodynamic parameters.
7. The method for predicting the temperature field of the volatilizing kiln based on the fusion of the thermodynamic mechanism and the infrared image data according to claim 1, wherein the parameter optimization model formula is as follows:
wherein N is 1 Is the sample size of the training set;
N 2 is the number of temperature points of the solid material;
N 3 is the number of effective temperature points in the infrared image;
d represents depth information of the kiln head region;
l is the axial length of the kiln body;
T s (x) The predicted temperature of the thermodynamic model solved at the axial position x;
Y t is extracted from infrared image processing resultSolid material temperature;
the predicted solid fluidized bed temperature is related to the unknown thermodynamic parameter theta u.t And unknown system parameter θ u.s Is a function of (2);
lower and upper represent the upper and lower limits, respectively, of the optimized parameter.
8. The method for predicting the temperature field of the volatilizing kiln based on the fusion of the thermodynamic mechanism and the infrared image data according to claim 1, wherein in the step S4, the flow rate, the kinematic viscosity and the density of the flue gas are used as model parameters to be optimized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310438344.XA CN116525014A (en) | 2023-04-23 | 2023-04-23 | Volatilizing kiln temperature field prediction method based on thermodynamic mechanism and infrared image data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310438344.XA CN116525014A (en) | 2023-04-23 | 2023-04-23 | Volatilizing kiln temperature field prediction method based on thermodynamic mechanism and infrared image data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116525014A true CN116525014A (en) | 2023-08-01 |
Family
ID=87402303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310438344.XA Pending CN116525014A (en) | 2023-04-23 | 2023-04-23 | Volatilizing kiln temperature field prediction method based on thermodynamic mechanism and infrared image data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116525014A (en) |
-
2023
- 2023-04-23 CN CN202310438344.XA patent/CN116525014A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111128313B (en) | Method and system for detecting FeO content of sinter | |
| CN107038307B (en) | The Roller Conveying Kiln for Temperature that mechanism is combined with data predicts integrated modelling approach | |
| Tang et al. | Temperature field prediction model for zinc oxide rotary volatile kiln based on the fusion of thermodynamics and infrared images | |
| Fan et al. | Predictive models and operation guidance system for iron ore pellet induration in traveling grate–rotary kiln process | |
| CN105574297A (en) | Self-adaption blast-furnace melt silicon content tendency forecasting method | |
| CN113517037B (en) | Method and system for predicting sintering ore FeO by fusing data and knowledge | |
| Cardoso et al. | Artificial neural networks for modelling and controlling the variables of a blast furnace | |
| CN111128312B (en) | Zinc oxide volatilization kiln mixed modeling method based on mechanism and support vector machine | |
| CN112365935B (en) | Cement free calcium soft measurement method based on multi-scale depth network | |
| CN116525014A (en) | Volatilizing kiln temperature field prediction method based on thermodynamic mechanism and infrared image data fusion | |
| CN114968997A (en) | Sintering end point forecasting method based on space-time feature extraction | |
| AU2009254074A1 (en) | Method of controlling a transformation process | |
| Bai et al. | Data-driven prediction of sinter composition based on multi-source information and LSTM network | |
| CN113627064B (en) | Roller kiln firing zone temperature prediction method based on mechanism and data mixed driving | |
| Xie et al. | A decomposition-based encoder-decoder framework for multi-step prediction of burn-through point in sintering process | |
| 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 | |
| Ye et al. | Tumble strength prediction for sintering: data-driven modeling and scheme design | |
| Qin et al. | The Reaction Rate Model of Volatile Kiln Based on SVR | |
| Zhao et al. | An end-to-end multi-source information fusion framework for f-cao content soft sensing in cement clinker burning process | |
| Chen et al. | Spatial feature learning based gaussian process regression for blast furnace raceway temperature prediction | |
| Wang et al. | TCN-LSTM: A Deep Learning-Based Temperature Prediction Model for Rotary Kilns | |
| Luo et al. | A Hybrid Modeling Method for Aluminum Smelting Process Based on a Hybrid Strategy-Based Sparrow Search Algorithm | |
| Sen-Hui et al. | A Hybrid Ensemble Model Based on ELM and Improved AdaBoost. RT Algorithm for Predicting the Iron Ore Sintering Characters | |
| Li et al. | Prediction of matte grade in the oxygen-rich top blown smelting based on WD-SSA-SVM algorithm |
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 |