CN117113836A - Steelmaking carbon dioxide blowing method and system based on double-pressure coupling - Google Patents
Steelmaking carbon dioxide blowing method and system based on double-pressure coupling Download PDFInfo
- Publication number
- CN117113836A CN117113836A CN202311078469.2A CN202311078469A CN117113836A CN 117113836 A CN117113836 A CN 117113836A CN 202311078469 A CN202311078469 A CN 202311078469A CN 117113836 A CN117113836 A CN 117113836A
- Authority
- CN
- China
- Prior art keywords
- carbon dioxide
- data
- steelmaking
- neural network
- network 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
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 title claims abstract description 396
- 229910002092 carbon dioxide Inorganic materials 0.000 title claims abstract description 198
- 239000001569 carbon dioxide Substances 0.000 title claims abstract description 198
- 238000009628 steelmaking Methods 0.000 title claims abstract description 97
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000007664 blowing Methods 0.000 title claims abstract description 49
- 230000008878 coupling Effects 0.000 title claims abstract description 27
- 238000010168 coupling process Methods 0.000 title claims abstract description 27
- 238000005859 coupling reaction Methods 0.000 title claims abstract description 27
- 238000003062 neural network model Methods 0.000 claims abstract description 62
- 230000008569 process Effects 0.000 claims abstract description 53
- 238000004519 manufacturing process Methods 0.000 claims abstract description 43
- 239000007788 liquid Substances 0.000 claims abstract description 42
- 238000009749 continuous casting Methods 0.000 claims abstract description 12
- 238000007670 refining Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 34
- 238000012360 testing method Methods 0.000 claims description 33
- 210000002569 neuron Anatomy 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 24
- 238000009834 vaporization Methods 0.000 claims description 16
- 230000008016 vaporization Effects 0.000 claims description 16
- 238000003723 Smelting Methods 0.000 claims description 14
- 229910000831 Steel Inorganic materials 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 14
- 239000010959 steel Substances 0.000 claims description 14
- 238000013480 data collection Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000005284 excitation Effects 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 12
- 230000001105 regulatory effect Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 abstract description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- PWHULOQIROXLJO-UHFFFAOYSA-N Manganese Chemical compound [Mn] PWHULOQIROXLJO-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000002309 gasification Methods 0.000 description 1
- 229910052748 manganese Inorganic materials 0.000 description 1
- 239000011572 manganese Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C5/00—Manufacture of carbon-steel, e.g. plain mild steel, medium carbon steel or cast steel or stainless steel
- C21C5/28—Manufacture of steel in the converter
- C21C5/30—Regulating or controlling the blowing
- C21C5/35—Blowing from above and through the bath
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C7/00—Treating molten ferrous alloys, e.g. steel, not covered by groups C21C1/00 - C21C5/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Organic Chemistry (AREA)
- Metallurgy (AREA)
- Materials Engineering (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Carbon Steel Or Casting Steel Manufacturing (AREA)
- Medical Informatics (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
Abstract
The invention provides a steelmaking carbon dioxide blowing method and a steelmaking carbon dioxide blowing system based on double pressure coupling. In the invention, in the production processes of top-bottom combined blowing of a carbon dioxide gas converter, carbon dioxide refining process production, carbon dioxide continuous casting process production and carbon dioxide gas ladle bottom blowing process production, gas carbon dioxide data, liquid carbon dioxide data and steel-making process data are collected, a BP neural network model is established, the gas carbon dioxide data and the liquid carbon dioxide data are coupled, the optimal gas-liquid two-phase carbon dioxide data can be obtained through the BP neural network model in the actual steel-making process, technical support is provided for actual steel-making, the pressure and flow change of the carbon dioxide gas-liquid two-phase are regulated in real time, and the application effect of carbon dioxide in the steel-making process is improved.
Description
Technical Field
The invention belongs to the field of metallurgical engineering, and particularly relates to a steelmaking carbon dioxide blowing method and system based on double pressure coupling.
Background
In the steelmaking process, carbon dioxide gas is blown into a molten pool in the furnace, carbon dioxide reacts with carbon and iron elements in molten steel to form an endothermic effect, and reacts with silicon and manganese elements in molten steel to form a micro-exothermic effect, so that the local temperature of an outlet area of a nozzle can be reduced, the temperature and the erosion speed of a bottom blowing element are controlled, a large amount of carbon monoxide bubbles are generated to enhance the stirring intensity of the molten pool, and the reaction dynamics condition in the furnace is improved. Especially in the processes of top-bottom combined blowing of a carbon dioxide gas converter, carbon dioxide gas refining process production, carbon dioxide gas continuous casting process production and carbon dioxide gas ladle bottom blowing process, the carbon dioxide can improve the steelmaking effect.
Adopts carbon dioxide to replace the traditional ladle bottom blowing N 2 Or Ar can effectively save energy and reduce emission, and actively realize a low-carbon development mode of the iron and steel industry. However, because the steelmaking process using carbon dioxide is relatively late in development, workers still need to control steelmaking process parameters of the carbon dioxide by means of manual experience to achieve a good process effect, and large-scale popularization and application of the steelmaking process using carbon dioxide are not facilitated. Therefore, a method for timely adjusting two-phase parameters of carbon dioxide gas and liquid in carbon dioxide steelmaking to achieve optimal steelmaking effect is needed.
Disclosure of Invention
Aiming at the technical problems, one of the purposes of the invention is to provide a steelmaking carbon dioxide blowing method based on double-pressure coupling, which is used for collecting gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data in the top-bottom combined blowing, carbon dioxide refining process production, carbon dioxide continuous casting process production and carbon dioxide ladle bottom blowing process production processes of a carbon dioxide converter, establishing a BP neural network model, obtaining optimal gas-liquid two-phase carbon dioxide data through the BP neural network model in the actual steelmaking process, providing technical support for the actual steelmaking and improving the application effect of carbon dioxide in the steelmaking process.
One of the purposes of one mode of the invention is to provide a steelmaking carbon dioxide blowing system based on double-pressure coupling, which comprises a vaporization device, a data collection module, a data preprocessing module, a model building module, a model optimizing module, an information transmission module and a digital management platform, wherein gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data are collected in the top and bottom combined blowing, carbon dioxide refining process production, carbon dioxide continuous casting process production and carbon dioxide ladle bottom blowing process production processes of a carbon dioxide converter, a BP neural network model is built, the optimal gas-liquid two-phase carbon dioxide data can be obtained through the BP neural network model in the actual steelmaking process, technical support is provided for the actual steelmaking, and the application effect of carbon dioxide in the steelmaking process is improved.
Note that the description of these objects does not prevent the existence of other objects. Not all of the above objects need be achieved in one embodiment of the present invention. Other objects than the above objects can be extracted from the description of the specification, drawings, and claims.
The present invention achieves the above technical object by the following means.
A steelmaking carbon dioxide blowing method based on double pressure coupling comprises the following steps:
step S1, data collection: converting the carbon dioxide liquid into carbon dioxide gas by using a vaporization device, and collecting gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data through sensors in the top-bottom combined blowing of a carbon dioxide gas converter, the production of a carbon dioxide gas refining process, the production of a carbon dioxide gas continuous casting process and the production of a carbon dioxide gas ladle bottom blowing process;
step S2, data preprocessing: the carbon dioxide data collected in the step S1 are marked in a connection way with corresponding steelmaking process data, and are divided into a training set and a testing set;
step S3, establishing a model: establishing a BP neural network model which is input into carbon dioxide data and output into steel-making process data, and coupling the gas carbon dioxide data and the liquid carbon dioxide data; the BP neural network model comprises an input layer, an implicit layer and an output layer; the input layer comprises three neurons, and gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data are respectively input;
step S4, model optimization: training the prediction model established in the step S3 by using the training set in the step S2, and testing the BP neural network model by using the testing set until the BP neural network model result accords with the testing set;
s5, steelmaking optimization: and (3) in the production processes of top-bottom combined blowing, carbon dioxide refining process production, carbon dioxide continuous casting process production and carbon dioxide ladle bottom blowing process production of the carbon dioxide gas converter, collecting carbon dioxide data through a sensor and inputting the carbon dioxide data into the BP neural network model optimized in the step (S4), and if the steelmaking process data output by the BP neural network model does not accord with smelting conditions, adjusting the data of carbon dioxide in steelmaking until the steelmaking process data output by the prediction model accord with smelting conditions, and carrying out steelmaking.
In the above scheme, the step S1 gas carbon dioxide data includes carbon dioxide gas pressure, carbon dioxide gas flow and vaporization capacity of the vaporization device; the liquid carbon dioxide data includes carbon dioxide liquid pressure, carbon dioxide liquid flow.
In the above scheme, the steelmaking process data in step S1 includes a molten steel temperature and a molten steel composition.
Further, the method for detecting the temperature and the composition of the molten steel is to take a sample in the process of production, and the sample is sent to a laboratory for detection.
In the above scheme, the BP neural network model in step S3 includes an input layer, an hidden layer and an output layer;
the input layer comprises two neurons, and gas carbon dioxide data and liquid carbon dioxide data are respectively input;
the number of the neuron nerves and the network of the hidden layer is determined by the following formula:
q=n+m+a
wherein m is the number of neurons of the output layer; n is the number of neurons of the input layer; q is the number of neurons in the hidden layer; a is a constant of 1-10;
all neurons of the neural network employ an S-type excitation function.
In the above scheme, the BP neural network model propagation process includes a forward propagation process and an error back propagation process.
Further, the back propagation process of the BP neural network model error comprises the following steps:
calculating the deviation between the expected output and the actual output obtained by the p-th training sample; calculating the mean square error of the output of the neuron when the P training sample is input as an objective function of the neural network; summing the objective functions of all training samples; selecting an S-shaped excitation function, reversely adjusting the weight and the threshold value of each layer by adopting a gradient descent method, and solving the weight of the minimum value of the objective function along the negative gradient direction of the sum of the objective functions of all training samples; and correcting the weights of all layers of the neural network according to the minimum weight of the solving objective function.
In the above scheme, the error between the BP neural network model result and the test set is less than 3% when the model is optimized in the step S4, and the BP neural network model result and the test set are considered to be in line with the test set.
In the above scheme, in the step S5, when the carbon dioxide is smelted, less than 5% of steel making process data output by the BP neural network model is considered to be in accordance with smelting conditions.
A system using the steelmaking carbon dioxide blowing method based on double pressure coupling comprises a vaporization device, a data collection module, a data preprocessing module, a model building module, a model optimizing module, an information transmission module and a digital management platform;
the vaporization device is used for converting carbon dioxide liquid into carbon dioxide gas;
the data collection module is used for collecting carbon dioxide data and steelmaking process data;
the data preprocessing module is used for marking the carbon dioxide data collected by the data collecting module in a linking way with corresponding steelmaking process data and dividing the carbon dioxide data into a training set and a testing set;
the model building module is used for building a BP neural network model which is input into carbon dioxide data and output into steelmaking process data;
the model optimization module is used for training the BP neural network model established by the model establishment module by using the training set divided by the data preprocessing module, and testing the BP neural network model by using the testing set until the output result of the BP neural network model accords with the testing set;
the information transmission module is used for transmitting the carbon dioxide data collected by the data collection module to the prediction model optimized by the model optimization module;
the digital management platform is used for adjusting the data of the carbon dioxide according to the steelmaking process data output by the BP neural network model until the steelmaking process data output by the BP neural network model accords with smelting conditions.
Compared with the prior art, the invention has the beneficial effects that:
according to one mode of the invention, in the top-bottom combined blowing, the carbon dioxide refining process production, the carbon dioxide continuous casting process production and the carbon dioxide ladle bottom blowing process production of the carbon dioxide gas converter, gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data are collected, a BP neural network model is established, optimal gas-liquid two-phase carbon dioxide data can be obtained through the BP neural network model in the actual steelmaking process, technical support is provided for the actual steelmaking, and the application effect of carbon dioxide in the steelmaking process is improved.
According to one mode of the invention, the steelmaking carbon dioxide blowing system based on double-pressure coupling is managed through the digital management platform, so that a worker can conveniently manage and monitor the carbon dioxide steelmaking process, and actual production is facilitated.
Note that the description of these effects does not hinder the existence of other effects. One embodiment of the present invention does not necessarily have all of the above effects. Effects other than the above are obvious and can be extracted from the description of the specification, drawings, claims, and the like.
Drawings
FIG. 1 is a schematic diagram of a method for blowing carbon dioxide in steelmaking based on double pressure coupling.
FIG. 2 is a schematic diagram of a data layer of a dual pressure coupling based steelmaking carbon dioxide blowing system of the present invention.
FIG. 3 is a schematic diagram of a digital management platform of the steelmaking carbon dioxide blowing system based on double pressure coupling.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "front", "rear", "left", "right", "upper", "lower", "axial", "radial", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element in question must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
FIG. 1 shows a preferred embodiment of the double pressure coupling-based steelmaking carbon dioxide blowing method, which comprises the following steps:
step S1, data collection: converting the carbon dioxide liquid into carbon dioxide gas by using a vaporization device, and collecting gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data through sensors in the top-bottom combined blowing of a carbon dioxide gas converter, the production of a carbon dioxide gas refining process, the production of a carbon dioxide gas continuous casting process and the production of a carbon dioxide gas ladle bottom blowing process;
the liquid carbon dioxide data information and the gas carbon dioxide data source are stored in the dewar, the flow and the pressure can be regulated and controlled, the liquid carbon dioxide is gasified into gas carbon dioxide through the gasification device and stored in the storage tank, the gas carbon dioxide can be regulated through the pressure valve and the flow valve, and the multiple pressure and the flow change are sources of the carbon dioxide data source.
Step S2, data preprocessing: the carbon dioxide data collected in the step S1 are marked in a connection way with corresponding steelmaking process data, and are divided into a training set and a testing set;
as shown in fig. 2, according to the present embodiment, CO is preferably paired at the data layer 2 The data source can be used again after pretreatmentPerforming data processing according to the prior art, distinguishing defect data which do not accord with actual production conditions, and eliminating the defect data from a training set and a testing set;
step S3, establishing a model: establishing a BP neural network model which is input into carbon dioxide data and output into steel-making process data, and coupling the gas carbon dioxide data and the liquid carbon dioxide data; the BP neural network model comprises an input layer, an implicit layer and an output layer; the input layer comprises three neurons, and gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data are respectively input;
step S4, model optimization: training the prediction model established in the step S3 by using the training set in the step S2, and testing the BP neural network model by using the testing set until the BP neural network model result accords with the testing set;
s5, steelmaking optimization: and (3) in the production processes of top-bottom combined blowing, carbon dioxide refining process production, carbon dioxide continuous casting process production and carbon dioxide ladle bottom blowing process production of the carbon dioxide gas converter, collecting carbon dioxide data through a sensor and inputting the carbon dioxide data into the BP neural network model optimized in the step (S4), and if the steelmaking process data output by the BP neural network model does not accord with smelting conditions, adjusting the data of carbon dioxide in steelmaking until the steelmaking process data output by the prediction model accord with smelting conditions, and carrying out steelmaking.
The step S1 of gas carbon dioxide data comprises carbon dioxide gas pressure, carbon dioxide gas flow and vaporization capacity of a vaporization device; the liquid carbon dioxide data includes carbon dioxide liquid pressure, carbon dioxide liquid flow.
The steel making process data in the step S1 comprise molten steel temperature and molten steel components.
The method for detecting the temperature and the composition of the molten steel is characterized in that in the process of production, a worker at a production line takes a sample, and the sample is sent to a laboratory for detection.
The BP neural network model in the step S3 comprises an input layer, an implicit layer and an output layer;
the input layer comprises two neurons, and gas carbon dioxide data and liquid carbon dioxide data are respectively input;
the number of the neuron nerves and the network of the hidden layer is determined by the following formula:
q=n+m+a
wherein m is the number of neurons of the output layer; n is the number of neurons of the input layer; q is the number of neurons in the hidden layer; a is a constant of 1 to 10.
All neurons of the neural network employ an S-type excitation function.
The BP neural network learning algorithm is a learning method supervised by a teacher, and comprises two different propagation processes, namely forward propagation and error reverse propagation. The input signal is propagated forward to the hidden node, and the output of the hidden node is propagated to the output node through the excitation function, so that an output result is given. And then correcting the weight and the threshold value of the network layer by layer from the output layer forward according to the direction of reducing the error between the expected output and the actual output until the input layer of the network, and repeating the steps until the minimum error is reached, wherein the BP algorithm is also called an error back propagation algorithm.
The BP neural network model propagation process comprises a forward propagation process and an error back propagation process.
The back propagation process of the BP neural network model error comprises the following steps:
calculating the deviation between the expected output and the actual output obtained by the p-th training sample; calculating the mean square error of the output of the neuron when the P training sample is input as an objective function of the neural network; summing the objective functions of all training samples; selecting an S-shaped excitation function, reversely adjusting the weight and the threshold value of each layer by adopting a gradient descent method, and solving the weight of the minimum value of the objective function along the negative gradient direction of the sum of the objective functions of all training samples; and correcting the weights of all layers of the neural network according to the minimum weight of the solving objective function.
According to this embodiment, preferably, the steps of the BP neural network model optimization learning algorithm include:
setting initial values of connection weights and thresholds of the network, wherein the initial values are random numbers between (-1, +1);
selecting a training sample, namely inputting gas carbon dioxide data and liquid carbon dioxide data as the training sample into an input layer;
forward propagation is carried out, and gas carbon dioxide data and liquid carbon dioxide data are propagated forward to obtain expected output;
error back propagation: reversely and sequentially calculating generalized error values of neurons of each layer from an output layer to an input layer, and then returning to the step 2) to sequentially calculate training samples;
weight and threshold correction: correcting the network weight and the threshold value of each layer;
and 2) returning to the step 2) for recalculating each learning sample according to the corrected network connection weight and the threshold value until the global error of the set network objective function is smaller than a preset value or the maximum learning times are reached, and ending learning.
And when the model is optimized in the step S4, the error between the BP neural network model result and the test set is less than 3 percent, and the BP neural network model result and the test set are considered to be in line with the test set.
And when the carbon dioxide is smelted in the step S5, less than 5% of steel making process data output by the BP neural network model is considered to accord with smelting conditions.
A steelmaking carbon dioxide blowing system based on double pressure coupling comprises a vaporization device, a data collection module, a data preprocessing module, a model building module, a model optimizing module, an information transmission module and a digital management platform;
the vaporization device is used for converting carbon dioxide liquid into carbon dioxide gas;
the data collection module is used for collecting carbon dioxide data and steelmaking process data;
the data preprocessing module is used for marking the carbon dioxide data collected by the data collecting module in a linking way with corresponding steelmaking process data and dividing the carbon dioxide data into a training set and a testing set;
the model building module is used for building a BP neural network model which is input into carbon dioxide data and output into steelmaking process data;
the model optimization module is used for training the BP neural network model established by the model establishment module by using the training set divided by the data preprocessing module, and testing the BP neural network model by using the testing set until the output result of the BP neural network model accords with the testing set;
the information transmission module is used for transmitting the carbon dioxide data collected by the data collection module to the prediction model optimized by the model optimization module;
the digital management platform is used for adjusting the data of the carbon dioxide according to the steelmaking process data output by the BP neural network model until the steelmaking process data output by the BP neural network model accords with smelting conditions.
As shown in FIG. 3, according to the present embodiment, the digital management platform may preferably be displayed on the UI digital platform layer on which the CO is exposed 2 Smelting process pressure and flow, molten steel composition and temperature and continuous casting CO 2 The process flow and pressure are convenient for the staff to watch and actually master the production condition.
It should be understood that although the present disclosure has been described in terms of various embodiments, not every embodiment is provided with a separate technical solution, and this description is for clarity only, and those skilled in the art should consider the disclosure as a whole, and the technical solutions in the various embodiments may be combined appropriately to form other embodiments that will be understood by those skilled in the art.
The above list of detailed descriptions is only specific to practical embodiments of the present invention, and they are not intended to limit the scope of the present invention, and all equivalent embodiments or modifications that do not depart from the spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. The steelmaking carbon dioxide blowing method based on double pressure coupling is characterized by comprising the following steps of:
step S1, data collection: converting the carbon dioxide liquid into carbon dioxide gas by using a vaporization device, and collecting gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data through sensors in the top-bottom combined blowing of a carbon dioxide gas converter, the production of a carbon dioxide gas refining process, the production of a carbon dioxide gas continuous casting process and the production of a carbon dioxide gas ladle bottom blowing process;
step S2, data preprocessing: the carbon dioxide data collected in the step S1 are marked in a connection way with corresponding steelmaking process data, and are divided into a training set and a testing set;
step S3, establishing a model: establishing a BP neural network model which is input into carbon dioxide data and output into steel-making process data, and coupling the gas carbon dioxide data and the liquid carbon dioxide data; the BP neural network model comprises an input layer, an implicit layer and an output layer; the input layer comprises three neurons, and gas carbon dioxide data, liquid carbon dioxide data and steelmaking process data are respectively input;
step S4, model optimization: training the prediction model established in the step S3 by using the training set in the step S2, and testing the BP neural network model by using the testing set until the BP neural network model result accords with the testing set;
s5, steelmaking optimization: and (3) in the production processes of top-bottom combined blowing, carbon dioxide refining process production, carbon dioxide continuous casting process production and carbon dioxide ladle bottom blowing process production of the carbon dioxide gas converter, collecting carbon dioxide data through a sensor and inputting the carbon dioxide data into the BP neural network model optimized in the step (S4), and if the steelmaking process data output by the BP neural network model does not accord with smelting conditions, adjusting the data of carbon dioxide in steelmaking until the steelmaking process data output by the prediction model accord with smelting conditions, and carrying out steelmaking.
2. The double pressure coupling-based steelmaking carbon dioxide blowing method as claimed in claim 1, wherein the step S1 gas carbon dioxide data includes carbon dioxide gas pressure, carbon dioxide gas flow rate and vaporization capacity of a vaporization device; the liquid carbon dioxide data includes carbon dioxide liquid pressure, carbon dioxide liquid flow.
3. The dual pressure coupling based steelmaking carbon dioxide blowing method as defined in claim 1 wherein said steelmaking process data of step S1 includes molten steel temperature and molten steel composition.
4. The method for blowing carbon dioxide in steelmaking based on double pressure coupling according to claim 3, wherein the method for detecting the temperature of molten steel and the composition of molten steel is characterized in that samples are taken in the process of production, and the samples are sent to a laboratory for detection.
5. The method for blowing carbon dioxide in steelmaking based on double pressure coupling according to claim 1, wherein the BP neural network model of step S3 comprises an input layer, an hidden layer and an output layer;
the input layer comprises two neurons, and gas carbon dioxide data and liquid carbon dioxide data are respectively input;
the number of the neuron nerves and the network of the hidden layer is determined by the following formula:
q=n+m+a
wherein m is the number of neurons of the output layer; n is the number of neurons of the input layer; q is the number of neurons in the hidden layer; a is a constant of 1-10;
all neurons of the neural network employ an S-type excitation function.
6. The dual pressure coupling based steelmaking carbon dioxide blowing method as defined in claim 1, wherein said BP neural network model propagation process comprises a forward propagation process and an error back propagation process.
7. The method for blowing carbon dioxide in steelmaking based on double pressure coupling according to claim 6, wherein said BP neural network model error back propagation process comprises the steps of:
calculating the deviation between the expected output and the actual output obtained by the p-th training sample; calculating the mean square error of the output of the neuron when the P training sample is input as an objective function of the neural network; summing the objective functions of all training samples; selecting an S-shaped excitation function, reversely adjusting the weight and the threshold value of each layer by adopting a gradient descent method, and solving the weight of the minimum value of the objective function along the negative gradient direction of the sum of the objective functions of all training samples; and correcting the weights of all layers of the neural network according to the minimum weight of the solving objective function.
8. The method for blowing carbon dioxide in steelmaking based on double pressure coupling according to claim 1, wherein the BP neural network model result and the test set error of less than 3% in the optimization of the model in the step S4 are regarded as conforming to the test set.
9. The method for blowing carbon dioxide in steelmaking based on double pressure coupling according to claim 1, wherein less than 5% of steelmaking process data output by the BP neural network model during the carbon dioxide smelting in the step S5 is considered to be in accordance with smelting conditions.
10. A system for using the double-pressure coupling-based steelmaking carbon dioxide blowing method as claimed in claims 1-9, which is characterized by comprising a vaporization device, a data collection module, a data preprocessing module, a model building module, a model optimizing module, an information transmission module and a digital management platform;
the vaporization device is used for converting carbon dioxide liquid into carbon dioxide gas;
the data collection module is used for collecting carbon dioxide data and steelmaking process data;
the data preprocessing module is used for marking the carbon dioxide data collected by the data collecting module in a linking way with corresponding steelmaking process data and dividing the carbon dioxide data into a training set and a testing set;
the model building module is used for building a BP neural network model which is input into carbon dioxide data and output into steelmaking process data;
the model optimization module is used for training the BP neural network model established by the model establishment module by using the training set divided by the data preprocessing module, and testing the BP neural network model by using the testing set until the output result of the BP neural network model accords with the testing set;
the information transmission module is used for transmitting the carbon dioxide data collected by the data collection module to the prediction model optimized by the model optimization module;
the digital management platform is used for adjusting the data of the carbon dioxide according to the steelmaking process data output by the BP neural network model until the steelmaking process data output by the BP neural network model accords with smelting conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311078469.2A CN117113836A (en) | 2023-08-25 | 2023-08-25 | Steelmaking carbon dioxide blowing method and system based on double-pressure coupling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311078469.2A CN117113836A (en) | 2023-08-25 | 2023-08-25 | Steelmaking carbon dioxide blowing method and system based on double-pressure coupling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117113836A true CN117113836A (en) | 2023-11-24 |
Family
ID=88807118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311078469.2A Pending CN117113836A (en) | 2023-08-25 | 2023-08-25 | Steelmaking carbon dioxide blowing method and system based on double-pressure coupling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117113836A (en) |
-
2023
- 2023-08-25 CN CN202311078469.2A patent/CN117113836A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108676955B (en) | A kind of BOF Steelmaking Endpoint carbon content and temprature control method | |
| CN109447346B (en) | Converter oxygen consumption prediction method based on gray prediction and neural network combined model | |
| US20220406413A1 (en) | Method for predicting yield of calcium in a calcium treatment process based on deep neural network | |
| CN109359723A (en) | Based on the converter terminal manganese content prediction technique for improving regularization extreme learning machine | |
| CN106119458A (en) | Converter steelmaking process cost control method based on BP neutral net and system | |
| CN115522012B (en) | Method for controlling TSC stage oxygen blowing amount of large converter | |
| CN113761787A (en) | Blast furnace molten iron silicon content online prediction method and system based on deep migration network | |
| CN113192568A (en) | Refining furnace desulfurization terminal point forecasting method and system | |
| CN109359320B (en) | Blast furnace index prediction method based on multiple sampling rate autoregressive distribution hysteresis model | |
| CN116738863B (en) | Method for building digital twin-based external refining CO2 digital management platform | |
| CN116384254A (en) | Error correction method and system for predicting molten steel temperature of LF refining furnace | |
| CN117745308B (en) | Special steel smelting process traceability optimization method based on product performance analysis | |
| CN117113836A (en) | Steelmaking carbon dioxide blowing method and system based on double-pressure coupling | |
| Fei et al. | Prediction of oxygen-blowing volume in BOF steelmaking process based on BP neural network and incremental learning | |
| CN112861276B (en) | Blast furnace burden surface optimization method based on data and knowledge dual drive | |
| CN103276136A (en) | Converter-steelmaking molten steel phosphorus-determination method based on sublance system | |
| CN113512620B (en) | Dynamic control method for endpoint carbon in whole converter smelting process of gas analysis and sublance | |
| CN102766730B (en) | Method for on-line prediction of total decarbonization amount of molten steel in circulating vacuum degassing method | |
| CN116911057A (en) | Real-time prediction method for temperature of molten pool in converter steelmaking converting process | |
| CN116127345B (en) | Converter steelmaking process mode design method based on deep clustering generation countermeasure network | |
| CN116663774A (en) | Converter process evaluation method and system based on digital twin | |
| CN113362903B (en) | Method for intelligently adding lime in TSC (thyristor switched capacitor) stage of large converter | |
| CN115564020A (en) | Oxygen lance position change state determination method, system, equipment and medium | |
| Rajesh et al. | Feed forward neural network for prediction of end blow oxygen in LD converter steel making | |
| Kang et al. | Prediction of end-point phosphorus content of molten steel in BOF with machine learning models |
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 |