CN112465223A - Blast furnace temperature state prediction method - Google Patents
Blast furnace temperature state prediction method Download PDFInfo
- Publication number
- CN112465223A CN112465223A CN202011350897.2A CN202011350897A CN112465223A CN 112465223 A CN112465223 A CN 112465223A CN 202011350897 A CN202011350897 A CN 202011350897A CN 112465223 A CN112465223 A CN 112465223A
- Authority
- CN
- China
- Prior art keywords
- blast furnace
- temperature
- furnace
- tuyere
- parameter
- 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 31
- 238000003062 neural network model Methods 0.000 claims abstract description 14
- 238000012512 characterization method Methods 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims description 21
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 16
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 9
- 229910052760 oxygen Inorganic materials 0.000 claims description 9
- 239000001301 oxygen Substances 0.000 claims description 9
- 229910052742 iron Inorganic materials 0.000 claims description 8
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 230000035699 permeability Effects 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims description 2
- 239000000463 material Substances 0.000 claims description 2
- 229910052710 silicon Inorganic materials 0.000 claims description 2
- 239000010703 silicon Substances 0.000 claims description 2
- 230000008859 change Effects 0.000 description 4
- XWHPIFXRKKHEKR-UHFFFAOYSA-N iron silicon Chemical compound [Si].[Fe] XWHPIFXRKKHEKR-UHFFFAOYSA-N 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000003723 Smelting Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 239000011572 manganese Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 229910000805 Pig iron Inorganic materials 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- WPBNNNQJVZRUHP-UHFFFAOYSA-L manganese(2+);methyl n-[[2-(methoxycarbonylcarbamothioylamino)phenyl]carbamothioyl]carbamate;n-[2-(sulfidocarbothioylamino)ethyl]carbamodithioate Chemical compound [Mn+2].[S-]C(=S)NCCNC([S-])=S.COC(=O)NC(=S)NC1=CC=CC=C1NC(=S)NC(=O)OC WPBNNNQJVZRUHP-UHFFFAOYSA-L 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 239000011593 sulfur Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21B—MANUFACTURE OF IRON OR STEEL
- C21B5/00—Making pig-iron in the blast furnace
-
- 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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21B—MANUFACTURE OF IRON OR STEEL
- C21B2300/00—Process aspects
- C21B2300/04—Modeling of the process, e.g. for control purposes; CII
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Organic Chemistry (AREA)
- Metallurgy (AREA)
- Materials Engineering (AREA)
- Manufacturing & Machinery (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Manufacture Of Iron (AREA)
- Waste-Gas Treatment And Other Accessory Devices For Furnaces (AREA)
Abstract
The invention discloses a method for predicting the temperature state of a blast furnace, which comprises the following steps: selecting a characteristic furnace temperature parameter; extracting image characteristic information representing the thermal state of the blast furnace tuyere from the blast furnace tuyere image data; selecting blast furnace parameters; establishing a neural network model by taking the image characteristic information representing the thermal state of the blast furnace tuyere and the selected blast furnace parameter as input and the representing furnace temperature parameter as output; training to obtain the image characteristic information and the correlation coefficient of the selected blast furnace parameter to the representation furnace temperature parameter at each lag time point; acquiring current blast furnace tuyere image data and selected blast furnace parameter data, inputting the trained neural network model, and outputting the characterization furnace temperature parameter data of each lag time point to realize furnace temperature prediction. The invention adds observable tuyere image information to carry out furnace temperature prediction, and provides a timely and reliable furnace temperature state prediction method for an operator.
Description
Technical Field
The invention relates to the field of blast furnace smelting, in particular to a method for predicting the temperature state of a blast furnace.
Background
The furnace temperature is an important state parameter in the production process of the blast furnace, and the over-high furnace temperature can cause the coke ratio to be increased, increase the cost of the blast furnace and reduce the service life of the blast furnace; when the furnace temperature is too low, the heat in the furnace is insufficient, the pig iron yield is reduced, and even the operation accidents such as furnace cooling and the like can be caused. In addition, the blast furnace is a large-lag system, and if adjustment measures are taken after the furnace temperature is obviously changed, the fluctuation of the furnace temperature is difficult to avoid. Therefore, the prediction of the furnace temperature is of great significance for the operation of the blast furnace.
The blast furnace is a high-pressure closed container, the internal state of the blast furnace can be judged mostly only by indirect means, and only the air inlet area is a place where the internal state of the blast furnace can be directly observed. The tuyere is positioned at the upper part of the hearth, the thermal state of the tuyere has important influence on the thermal state of the hearth, and generally, an operator can judge the current thermal state of the tuyere by directly observing the brightness degree of the tuyere of the blast furnace and the current thermal state is taken as an important condition for judging the thermal state change of the hearth. However, since there are many blast furnace tuyeres and it is difficult to simultaneously and comprehensively observe the blast furnace tuyeres even when a tuyere camera is mounted, the condition is rarely considered in various studies, and important information is lost. Moreover, the running condition of the blast furnace is complex, and the accuracy of model analysis is influenced by the change of production and operation conditions.
At present, the furnace temperature forecasting mode is mainly based on mathematical model forecasting of operation data, but the blast furnace operation condition is complex, various conditions change along with the production condition, and the model is interfered by various uncertain factors, so that a large deviation is generated during forecasting.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the present invention provides a method for predicting the furnace temperature status of a blast furnace, which can effectively combine the tuyere data to reduce the deviation of the furnace temperature status prediction and provide reliable help for the operation of the blast furnace in time.
In order to achieve the aim, the invention provides a method for predicting the temperature state of a blast furnace, which comprises the following steps:
step S1: selecting a characteristic furnace temperature parameter;
step S2: extracting image characteristic information representing the thermal state of the blast furnace tuyere from the blast furnace tuyere image data;
step S3: selecting blast furnace parameters, wherein the blast furnace parameters comprise operating parameters and state parameters of a blast furnace;
step S4: establishing a neural network model, wherein the neural network model takes the image characteristic information representing the thermal state of the blast furnace tuyere, the blast furnace parameters selected in the step S3 as input, and the representation furnace temperature parameters selected in the step S1 as output; training to obtain the image characteristic information representing the hot state of the blast furnace tuyere and the correlation coefficient of the blast furnace parameter selected in the step S3 to the representation furnace temperature parameter selected in the step S1 at each lag time point;
step S5: acquiring current blast furnace tuyere image data and blast furnace parameter data, inputting the trained neural network model, and outputting the characterization furnace temperature parameter data of each lag time point to realize furnace temperature prediction.
Further, the characterizing furnace temperature parameters comprise molten iron temperature and molten iron silicon content.
Further, the image characteristic information representing the thermal state of the blast furnace tuyere is the average gray value of the tuyere of the blast furnace.
Further, the extraction of the average gray value of the tuyere comprises the following steps:
step S21: converting the images of the air ports into gray level images, and removing image noise of the gray level images to obtain gray level values of the air ports;
step S22: and carrying out mean value processing on the gray values of the air ports to obtain the average gray value of the air ports.
For convenience of computer processing, each tuyere image of the blast furnace is converted into a gray scale image, and the current furnace temperature is represented by the tuyere gray scale value. Meanwhile, the blast furnace is provided with a plurality of tuyeres, so that the gray information of all the tuyere images of the blast furnace is comprehensively averaged to reflect the average condition of the thermal state of the tuyere of the whole blast furnace and is used as an input condition of a neural network model to carry out model analysis, and the accuracy of the model is improved.
Further, the blast furnace parameters selected in step S3 include: air quantity, air temperature, hot air pressure, blast furnace permeability index, oxygen enrichment rate and material speed.
Further, in step S3, the blast furnace parameters are extracted by correlation analysis, and the extraction is selected according to the correlation between each blast furnace parameter and the characteristic furnace temperature parameter, and the correlation between each blast furnace parameter and the corresponding correlation between each blast furnace parameter.
The method can select a plurality of blast furnace parameters with high correlation coefficients with the characteristic furnace temperature parameters, and select one of the blast furnace parameters with high correlation coefficients among the blast furnace parameters, so as to reduce the selection of invalid parameters.
Further, the correlation analysis in the step S3 adopts a multiple linear regression algorithm
Further, the neural network is one of a BP neural network, a wavelet neural network and an RBF neural network.
According to the method for predicting the furnace temperature state of the blast furnace, the image characteristic information representing the thermal state of the tuyere is extracted by collecting the image data of the tuyere and is used as the input parameter of the neural network to jointly participate in furnace temperature prediction, so that the deviation of furnace temperature state prediction can be effectively reduced, and reliable help is provided for the operation of the blast furnace in time.
Drawings
Fig. 1 is a flowchart of a method for predicting a temperature state of a blast furnace according to the present invention.
Detailed Description
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. Those skilled in the art will appreciate still other possible embodiments and advantages of the present invention with reference to these figures. Elements in the figures are not drawn to scale and like reference numerals are generally used to indicate like elements.
The invention will now be further described with reference to the accompanying drawings and detailed description.
As shown in fig. 1, the present invention discloses a specific embodiment of a method for predicting a temperature state of a blast furnace, which comprises the following steps:
step S1: selecting a characteristic furnace temperature parameter;
step S2: extracting image characteristic information representing the thermal state of the blast furnace tuyere from the blast furnace tuyere image data;
step S3: selecting blast furnace parameters, wherein the blast furnace parameters comprise operating parameters and state parameters of a blast furnace;
step S4: establishing a neural network model, wherein the neural network model takes the image characteristic information representing the thermal state of the blast furnace tuyere, the blast furnace parameters selected in the step S3 as input, and the representation furnace temperature parameters selected in the step S1 as output; training to obtain the image characteristic information representing the hot state of the blast furnace tuyere and the correlation coefficient of the blast furnace parameter selected in the step S3 to the representation furnace temperature parameter selected in the step S1 at each lag time point;
step S5: acquiring current blast furnace tuyere image data and blast furnace parameter data, inputting the trained neural network model, and outputting the characterization furnace temperature parameter data of each lag time point to realize furnace temperature prediction.
The method for predicting the furnace temperature state of the blast furnace, which is exemplified in the embodiment, is characterized in that observable tuyere image information is added, and furnace temperature prediction is carried out through a neural network model, so that a timely and reliable furnace temperature state prediction method is provided for an operator.
The steps are now detailed as follows:
in step S1, the parameters currently used for characterizing the furnace temperature mainly include the molten iron temperature and the molten iron silicon content, which may be selected alternatively or together.
Step S2: and extracting image characteristic information representing the thermal state of the blast furnace tuyere from the blast furnace tuyere image data.
The method specifically comprises the following steps:
(1) and converting the blast furnace tuyere image into a gray scale image.
Preferably, the method of converting the blast furnace tuyere image into the gray scale map may employ a maximum value method, an average value method, a weighted average value method, and the like. The weighted average method is beneficial to improving the sharpness of the gray level image and improving the accuracy of threshold discrimination.
(2) And removing image noise in the gray-scale image.
Preferably, the pattern denoising can be performed by means of a mean filter, a morphological noise filter, a wavelet denoising, and the like, which are all known pattern denoising means and will not be described herein.
(3) And carrying out mean processing on the gray value of the gray map to obtain the average gray value of the tuyere, wherein the average gray value of the tuyere is image characteristic information representing the thermal state of the tuyere of the blast furnace.
In step S3, selecting an operation parameter and a state parameter outside a tuyere image of the blast furnace for correlation analysis, wherein the parameter to be selected includes: air quantity, air speed, air temperature, hot air pressure, blast furnace permeability index, pressure difference, oxygen enrichment rate, coal injection quantity, water temperature difference, furnace top gas CO2, furnace top gas CO, [ Mn ], [ P ], [ S ], fuel ratio, blast furnace load, blast furnace charge speed and the like. Wherein [ Mn ], [ P ], [ S ] respectively represent the contents of components such as manganese, phosphorus, sulfur and the like in the molten iron.
The blast furnace is a large-lag, non-linear system, and in fact, besides the gray-scale values of the tuyere image, all blast furnace parameters have hysteresis on the furnace temperature. Generally, the hysteresis of a certain relevant parameter can be determined by referring to the practical experience of blast furnace experts or by solving the relevant coefficient by adopting a multiple linear regression method.
Specifically, the method for solving the correlation coefficient by adopting the multiple linear regression comprises the following steps:
let the parameter affecting the furnace temperature change be xi(i-1, 2, …, n) and a value of molten iron temperature or silicon content yi(i ═ 1,2, …, n), and the parameter lag time series is T (0.5h, 1h, 2h, 2.5h, …), then at a certain lag time T, the correlation coefficient r (T) is obtained by linear regression:
and obtaining the correlation coefficient of each blast furnace parameter to the furnace temperature at each lag time point, wherein the point with the maximum correlation coefficient is the lag time of the parameter.
In this embodiment, the selected blast furnace parameters include, according to the correlation analysis: the air quantity, the air temperature, the hot air pressure, the blast furnace permeability index, the oxygen enrichment rate, the blast furnace charge speed and the like are closely related to the molten iron temperature and the molten iron silicon content, and the correlation degree among all blast furnace parameters is low.
Wherein, the air volume refers to the volume (m3/min or m3/h) of air entering the blast furnace in a standard state in unit time; the blast temperature is the blast air temperature heated to the temperature by a hot blast stove in blast furnace ironmaking, usually to the high blast temperature, the high blast temperature is the operation of heating the blast air temperature to more than 1200 ℃ by the hot blast stove in modern blast furnace ironmaking, which can reduce the fuel consumption and increase the steel yield; the blast furnace permeability index is: the ratio of air quantity to total pressure difference (i.e. the difference between hot air pressure and furnace top pressure) in the blast furnace smelting process; the blast furnace burden velocity refers to the descending velocity of the burden in the movement process of the blast furnace burden; the oxygen enrichment rate is the amount of oxygen in the blast air, expressed as a percentage, which is higher than the oxygen content of the atmosphere; oxygen-rich blasting helps to increase the utilization factor of the blast furnace.
In the present embodiment, a specific example of step S4 is given: and establishing and training a neural network model by taking the average gray value of a tuyere of the blast furnace, the air quantity, the air temperature, the hot air pressure, the air permeability index of the blast furnace, the oxygen enrichment rate and the blast furnace burden speed as input and taking the molten iron temperature and the molten iron silicon content as output.
Preferably, in step S3, the neural network may be a classified neural network such as a BP neural network, a wavelet neural network, or an RBF neural network.
The BP neural network has arbitrary complex pattern classification capability and excellent multidimensional function mapping capability, and solves the problems of XOR and other problems which cannot be solved by a simple perceptron. Structurally, the BP network has an input layer, a hidden layer, and an output layer; basically, the BP algorithm calculates the minimum value of an objective function by using a network error square as the objective function and adopting a gradient descent method. Therefore, the BP neural network is suitable for predicting the temperature state of the blast furnace.
The RBF neural network is a special BP neural network, hidden nodes of the RBF neural network adopt the distance (such as Euclidean distance) between an input mode and a central vector as an argument of a function, and use a radial basis function (such as Gaussian function) as an activation function. The further away the input of a neuron is from the center of the radial basis function, the lower the activation degree of the neuron (gaussian function). The output of the RBF network is related to partial tuning parameters, and the RBF neural network has a local mapping characteristic and is also suitable for predicting the temperature state of the blast furnace.
In summary, the blast furnace temperature state prediction method provided by the invention extracts the image characteristic information representing the thermal state of the tuyere by collecting the tuyere image data, and takes the image characteristic information as the input parameter of the neural network to participate in furnace temperature prediction together, so that the deviation of furnace temperature state prediction can be effectively reduced, and reliable help is provided for the blast furnace operation in time.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. The method for predicting the temperature state of the blast furnace is characterized by comprising the following steps of:
step S1: selecting a characteristic furnace temperature parameter;
step S2: extracting image characteristic information representing the thermal state of the blast furnace tuyere from the blast furnace tuyere image data;
step S3: selecting blast furnace parameters, wherein the blast furnace parameters comprise operating parameters and state parameters of a blast furnace;
step S4: establishing a neural network model, wherein the neural network model takes the image characteristic information representing the thermal state of the blast furnace tuyere, the blast furnace parameters selected in the step S3 as input, and the representation furnace temperature parameters selected in the step S1 as output; training to obtain the image characteristic information representing the hot state of the blast furnace tuyere and the correlation coefficient of the blast furnace parameter selected in the step S3 to the representation furnace temperature parameter selected in the step S1 at each lag time point;
step S5: acquiring current blast furnace tuyere image data and blast furnace parameter data, inputting the trained neural network model, and outputting the characterization furnace temperature parameter data of each lag time point to realize furnace temperature prediction.
2. The method for predicting the temperature state of the blast furnace according to claim 1, wherein: the characterization furnace temperature parameters comprise the temperature of molten iron and the silicon content of the molten iron.
3. The method for predicting the temperature state of the blast furnace according to claim 1, wherein: and the image characteristic information representing the thermal state of the blast furnace tuyere is the average gray value of the tuyere of the blast furnace.
4. The method for predicting the temperature state of the blast furnace according to claim 3, wherein the extracting of the average gray value of the tuyere comprises the steps of:
step S11: converting the images of the air ports into gray level images, and removing image noise of the gray level images to obtain gray level values of the air ports;
step S12: and carrying out mean value processing on the gray values of the air ports to obtain the average gray value of the air ports.
5. The method for predicting the furnace temperature status of a blast furnace according to claim 1, wherein the blast furnace parameters selected in step S3 include: air quantity, air temperature, hot air pressure, blast furnace permeability index, oxygen enrichment rate and material speed.
6. The method for predicting the temperature state of the blast furnace according to claim 5, wherein: in the step S3, the blast furnace parameters are extracted by correlation analysis, and the extraction is performed according to the correlation coefficient between each blast furnace parameter and the characteristic furnace temperature parameter, and the correlation coefficient between each blast furnace parameter.
7. The method for predicting the temperature state of the blast furnace according to claim 6, wherein: the correlation analysis in step S3 adopts a multiple linear regression algorithm.
8. The method for predicting the temperature state of the blast furnace according to claim 1, wherein: the neural network is one of a BP neural network, a wavelet neural network and an RBF neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011350897.2A CN112465223A (en) | 2020-11-26 | 2020-11-26 | Blast furnace temperature state prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011350897.2A CN112465223A (en) | 2020-11-26 | 2020-11-26 | Blast furnace temperature state prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112465223A true CN112465223A (en) | 2021-03-09 |
Family
ID=74808698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011350897.2A Pending CN112465223A (en) | 2020-11-26 | 2020-11-26 | Blast furnace temperature state prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465223A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114626303A (en) * | 2022-03-18 | 2022-06-14 | 山东莱钢永锋钢铁有限公司 | Blast furnace temperature prediction and operation guidance method based on neural network |
| CN115495982A (en) * | 2022-09-21 | 2022-12-20 | 中冶南方工程技术有限公司 | Blast furnace temperature prediction method, terminal equipment and storage medium |
| CN115687872A (en) * | 2022-09-08 | 2023-02-03 | 江苏华鹰光电科技有限公司 | Blast furnace hearth thermal state trend pre-judging method |
| WO2024060289A1 (en) * | 2022-09-21 | 2024-03-28 | 中冶南方工程技术有限公司 | Method for automatically adjusting furnace temperature of blast furnace, terminal device, and storage medium |
| CN117806169A (en) * | 2024-01-17 | 2024-04-02 | 北京工业大学 | Furnace temperature early warning optimization method, system, terminal and medium based on neural network |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104498654A (en) * | 2014-12-29 | 2015-04-08 | 燕山大学 | Blast furnace temperature change trend determination method and device |
-
2020
- 2020-11-26 CN CN202011350897.2A patent/CN112465223A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104498654A (en) * | 2014-12-29 | 2015-04-08 | 燕山大学 | Blast furnace temperature change trend determination method and device |
Non-Patent Citations (3)
| Title |
|---|
| 崔桂梅等: "基于改进PSO-KELM的高炉回旋区温度预测研究", 《中国测试》 * |
| 王炜等: "考虑时滞的铁水硅含量预报模型", 《山东冶金》 * |
| 范刚龙等: "神经网络模型预报炉温的研究", 《武汉理工大学学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114626303A (en) * | 2022-03-18 | 2022-06-14 | 山东莱钢永锋钢铁有限公司 | Blast furnace temperature prediction and operation guidance method based on neural network |
| CN115687872A (en) * | 2022-09-08 | 2023-02-03 | 江苏华鹰光电科技有限公司 | Blast furnace hearth thermal state trend pre-judging method |
| CN115495982A (en) * | 2022-09-21 | 2022-12-20 | 中冶南方工程技术有限公司 | Blast furnace temperature prediction method, terminal equipment and storage medium |
| WO2024060289A1 (en) * | 2022-09-21 | 2024-03-28 | 中冶南方工程技术有限公司 | Method for automatically adjusting furnace temperature of blast furnace, terminal device, and storage medium |
| CN117806169A (en) * | 2024-01-17 | 2024-04-02 | 北京工业大学 | Furnace temperature early warning optimization method, system, terminal and medium based on neural network |
| CN117806169B (en) * | 2024-01-17 | 2024-06-04 | 北京工业大学 | Furnace temperature early warning optimization method, system, terminal and medium based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112465223A (en) | Blast furnace temperature state prediction method | |
| CN104630410B (en) | A kind of pneumatic steelmaking quality real-time dynamic forecast method based on data parsing | |
| CN112819802B (en) | Method for supervising and predicting blast furnace condition abnormality based on tuyere information deep learning | |
| CN107330597B (en) | Multi-dimensional evaluation method for energy consumption state of blast furnace hot blast stove based on fuzzy pattern recognition | |
| CN110427715B (en) | Method for predicting furnace hearth thermal state trend based on time sequence and multiple dimensions of blast furnace | |
| Sala et al. | Multivariate time series for data-driven endpoint prediction in the basic oxygen furnace | |
| CN111444963A (en) | Blast furnace molten iron silicon content prediction method based on SSA-SVR model | |
| JPWO2020152993A1 (en) | Metal material design support method, prediction model generation method, metal material manufacturing method, and design support device | |
| Han et al. | Hybrid intelligent control of BOF oxygen volume and coolant addition | |
| Cardoso et al. | Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning | |
| CN107808221A (en) | Blast furnace material distribution Parameter Decision Making method based on case matching | |
| CN102968644A (en) | Method for predicting smelting finishing point of argon-oxygen refined iron alloy | |
| CN113517037A (en) | Method and system for predicting sintering ore FeO by fusing data and knowledge | |
| CN113033704A (en) | Intelligent judging method for copper converter converting copper making period end point based on pattern recognition | |
| CN111344420A (en) | Blast control device and method for blast furnace | |
| CN111798023A (en) | Method for predicting comprehensive coke ratio in steelmaking sintering production | |
| CN116911057A (en) | Real-time prediction method for temperature of molten pool in converter steelmaking converting process | |
| Yang et al. | Multisource Information Fusion for Autoformer: Soft Sensor Modeling of FeO Content in Iron Ore Sintering Process | |
| CN112734722B (en) | Flame endpoint carbon content prediction method based on improved complete local binary pattern | |
| CN113033705B (en) | Intelligent judgment and verification method for copper converter blowing slagging period end point based on pattern recognition | |
| Zhang et al. | Prediction of blast furnace fuel ratio based on back‐propagation neural network and K‐Nearest neighbor algorithm | |
| CN103160629A (en) | Method for prediction of blast furnace heat tendency | |
| CN113570145A (en) | Prediction method for temperature of dead material column of iron-making blast furnace core | |
| Sun et al. | A blowing endpoint judgment method for converter steelmaking based on improved DenseNet | |
| CN112396101A (en) | Intelligent image analysis and decision-making method based on firepower plant hearth flame television |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210309 |
|
| RJ01 | Rejection of invention patent application after publication |