Method for intelligently producing stainless steel by combining RKEF smelting and double-roll thin-strip cast-rolling process

Abstract

The invention relates to the technical field of thin-strip continuous casting, in particular to an intelligent stainless steel production method combining RKEF smelting and a double-roller thin-strip cast rolling technology.According to the method, the RKEF technology is directly coupled with the stainless steel refining and thin-strip continuous casting technology, firstly, based on target product requirements, an intelligent batching model is adopted for calculating furnace charge of an RKEF furnace; then, based on RKEF molten nickel iron components, an intelligent batching model is adopted to conduct collaborative optimization calculation on added ingredients of the AOD furnace (a dynamic blowing control model is adopted to conduct real-time optimization on the proportion and flow of mixed gas of O2, Ar and N2), and cost optimal dynamic batching under multiple constraints is achieved; then, a neural network algorithm GAN with physical constraint PI is used for predicting components and temperature, predicted values of the components and the temperature and control instructions are output, the metallurgical physical law is used as hard constraint to be embedded into model training, a control decision is made to fit data and conform to scientific rules, process control is conducted accurately, the whole process is more energy-saving, and the method is suitable for large-scale popularization and application. And carbon dioxide emission is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of thin strip continuous casting, and particularly relates to a method for intelligently producing stainless steel by combining RKEF smelting and a double-roller thin strip casting process. BACKGROUND

[0002] A traditional stainless steel strip preparation process includes: electric furnace / AOD furnace smelting; continuous casting slab; hot rolling; cold rolling; annealing. The entire process is long, has high energy consumption (comprehensive energy consumption > 500 kgce / ton) and CO2 emission > 2 tons / ton of steel.

[0003] In the prior art, there are also some innovations, such as: Patent No. ZL201310619500.9 and patent name A new RKEF process for producing high-strength short-process energy-saving ferronickel alloy discloses the following steps: (1) drying; (2) batching; (3) roasting-pre-reduction; (4) electric furnace smelting; (5) casting forming, and the application also discloses a new RKEF process for producing high-strength short-process energy-saving ferronickel alloy equipment, which mainly comprises a rotary kiln, a drying kiln, an electric furnace workshop, a transfer station, a batching station and a raw material warehouse. One end of the rotary kiln is connected with the electric furnace workshop, the other end of the rotary kiln is connected with the transfer station, the drying kiln is located below the rotary kiln, one end of the drying kiln is connected with the electric furnace workshop, one end of the transfer station away from the rotary kiln is connected with the batching station, and the raw material warehouse is connected with one end of the drying kiln close to the electric furnace workshop through a belt conveyor. The patent only changes the process steps and optimizes the production equipment such as the rotary kiln, the drying kiln and the electric furnace, and does not apply the RKEF and double-roller thin strip direct continuous casting method.

[0004] Patent No. ZL201710009624.3 and patent name A method for producing ferronickel by adopting a rotary kiln direct reduction RKEF combined method discloses the following steps: drying red clay nickel ore for standby; taking a proper amount of dried red clay nickel ore, crushing, screening and mixing with carbonaceous reducing agent and dolomite to obtain mixed material A, and the mass percentage of the carbonaceous reducing agent in the mixed material A is 17-25%; the mixed material A is made into pellets and sent into a first rotary kiln for roasting, and the roasted sand is screened and treated to obtain coarse ferronickel particles containing 50-60% of slag; the coarse ferronickel particles are mixed with dried red clay nickel ore and limestone and sent into a second rotary kiln for roasting, and the roasted sand is directly put into an electric furnace for melting, the secondary voltage of the electric furnace is 275-315 V, the primary current is 380-420 A, the temperature of the molten iron in the electric furnace is 1500-1540℃, and molten iron containing ferronickel is obtained. The patent adopts a two-stage rotary kiln design, the first kiln is used for high-reducing agent ratio to strengthen direct reduction, the second kiln is used for RKEF, the electric furnace is operated at low voltage and high current, and the nickel recovery rate of 93.5% is a highlight, but the complexity of the process is increased.

[0005] The process principle of thin strip casting technology is to directly cast molten steel between a pair of counter-rotating and internally water-cooled crystallization rollers, the molten pool liquid level exists in the closed space composed of two side sealing plates and roller surfaces, and the molten steel solidifies between the two rollers to form a thin strip. Compared with the traditional continuous casting process, the thin strip casting technology has the advantages of short process, low production cost, energy saving and environmental protection, etc., and can directly cast and roll the molten steel into a strip steel with a thickness of 0.5-6mm without the need for reheating treatment. Therefore, an intelligent stainless steel production method combining RKEF smelting and double-roller thin strip casting process is designed to solve the problems existing in the prior art. SUMMARY

[0006] The purpose of the present application is to provide an intelligent stainless steel production method combining RKEF smelting and double-roller thin strip casting process, and the specific technical solutions are as follows: An intelligent stainless steel production method combining RKEF smelting and double-roller thin strip casting process, comprising the following steps: First step, based on the target product demand, an intelligent batching model is used to calculate the furnace charge of the RKEF furnace; the prepared furnace charge is loaded into the RKEF system, and the nickel iron melt with controllable composition and temperature is obtained by smelting; Second step, the nickel iron melt obtained in the first step is hot charged to the AOD furnace through the ladle; based on the composition of the RKEF nickel iron melt, an intelligent batching model is used to cooperatively optimize and calculate the addition of the AOD furnace, and a dynamic blowing control model is used to real-time optimize the proportion and flow of O2, Ar and N2 mixed gas, to carry out desiliconization, decarburization and dephosphorization reactions, and obtain primary refined molten steel; Third step, the LF furnace receives the primary refined molten steel from the AOD furnace, and uses a neural network algorithm with physical constraints GAN to intelligently control the composition and temperature; after refining, refined molten steel is obtained, which specifically includes: Step 3.1, the LF furnace refines the received molten steel; Step 3.2, using an instrument assembly to obtain molten steel temperature data, three-phase electrode data, molten steel composition data and slag composition, forming a data set; Step 3.3, using a neural network algorithm with physical constraints GAN to predict the composition and temperature, outputting the predicted values of the composition and temperature and control instructions; Step 3.4, judging the composition and temperature predicted in step 3.3, if the composition and temperature meet the standards, then entering the fourth step; if the composition and temperature do not meet the standards, then adding the required alloy for composition accurate fine tuning and combining the control instructions, returning to step 3.1; Fourth step, the refined molten steel obtained in the third step is injected into the flow distributor system of the double-roller thin strip casting through the tundish; the refined molten steel is cast and rolled by the double-roller to obtain an initial thin strip blank; Fifth step, cooling the initial thin strip blank obtained in the fourth step to obtain a stainless steel thin strip.

[0007] Preferably, the furnace charge is obtained by taking laterite nickel ore as the main raw material and adding chromium ore, limestone, dolomite, quartzite, coke and coal; the charging includes at least one of waste stainless steel, high-carbon chromium iron, nickel iron / nickel plate, flux and reducing agent.

[0008] Preferably, the dynamic blowing control model is a decision model based on reinforcement learning, which dynamically adjusts the mixing ratio and flow of O2, Ar and N2 by real-time monitoring of furnace gas composition, flue gas temperature, molten pool temperature and sound signal.

[0009] Preferably, the intelligent charging model is a long short-term memory network model optimized by the CPO algorithm, and the charging calculation includes the following steps: Step 2.1, collect data and create a data set, specifically: the input features of the data set are the target values of the target steel C, Si, Mn, P, S, Cr, Ni elements, the composition of the raw materials used, the composition and weight of the RKEF molten iron; the output label is the proportion of each raw material; Step 2.2, pre-process the data including cleaning, normalization and missing value processing to obtain a high-quality data set; Step 2.3, initially select a long short-term memory network LSTM as an initial model; combine the high-quality data set to search for the optimal super parameter combination of the initial model by using the CPO algorithm to obtain an intelligent charging model; Step 2.4, using the intelligent charging model to calculate the charging, output the required materials and the corresponding amount.

[0010] Preferably, in step 3.2: use an infrared thermometer and a thermocouple to obtain molten steel temperature data; use a voltage current transformer to obtain voltage, current and power of the three-phase electrode; use an online spectrometer to obtain molten steel composition data; use an online slag detector to obtain slag composition, including CaO, SiO2, Al2O3, MgO, FeO, MnO and S.

[0011] Preferably, in the neural network algorithm GAN with physical constraints in step 3.3, the metallurgical reaction kinetics equation is used as a loss function for physical constraint, as follows: ; ; ; ; ; wherein: , , is the constraint weight of adaptive adjustment; is the total physical loss term; is the energy conservation constraint term; is the mass transfer constraint term; is the slag-steel reaction constraint term; is the specific heat capacity of molten steel at constant pressure; m is the mass of molten steel in the ladle; is the change rate of the bath temperature; is the thermal efficiency of the LF furnace; is the arc voltage; is the arc current, is the power factor; is the total heat loss of the system; are alloying elements C, Si, Mn, P, S, Cr and Ni; is the concentration of element ; is the change rate of the concentration of element ; is the mass transfer coefficient of element ; is the total surface area of the alloying elements ; is the density of molten steel, is the saturation concentration of element in molten steel; is the current concentration of element ; is the sulfur distribution ratio; is the sulfur content in the slag; is the sulfur content in the molten steel; is the equilibrium constant of the desulfurization reaction; is the activity of CaO in the slag; is the activity coefficient of S in the molten steel; is the activity of O in the molten steel; is the content of P in the molten steel; is the initial P content in the molten steel; is the rate constant of the rephosphorization reaction; is time.

[0012] Preferably, the control instructions in step 3.4 include: the feeding speed of the corresponding feeding machine for low-carbon chromium iron, nickel iron and molybdenum iron; the feeding amount of the corresponding feeding machine for calcium carbide and aluminum particles; the argon blowing flow of the argon control valve; and the arc power of the electrode controller.

[0013] Preferably, the sixth step is thin strip intelligent defect detection and analysis, which comprises the following steps: Step 6.1, obtaining defects and positions of the stainless steel thin strip by using an online visual detection system; Step 6.2. Incorporate the defect quality composite score as a means of identifying the defect type and quantifying its severity based on the defect quality composite score obtained in step 6.2.

[0014] Preferably, the defect quality composite score in step 6.2 is calculated using the following equation: ; ; wherein: is the defect quality composite score; is the defect category index, wherein: 1 is edge crack, 2 is subsurface porosity, 3 is oscillation, and 4 is concave; is the total number of defect categories, is the weight coefficient; is the probability value output by the model that the defect is of the th category; is a custom function for calculating defect severity; represents the physical characteristics of the defect.

[0015] Preferably, the custom function for calculating defect severity is as follows: ; ; ; ; wherein: is the custom function for crack severity; crack_length is the crack length; L_critical is the critical length threshold; is the custom function for subsurface porosity severity; Avg_diameter_porosity is the average diameter of the porosity; D_porosity_critical is the critical threshold for diameter; is the custom function for oscillation severity; max_depth_oscillation is the maximum depth of the oscillation; D_oscillation_critical is the critical threshold for oscillation depth; is the custom function for concave severity; Depth_concave is the depth of the concave; D_critical_concave is the critical threshold for concave depth; Area_concave is the area of the concave; A_critical_concave is the critical threshold for concave area.

[0016] The disclosed intelligent stainless steel production method combined with RKEF smelting and double-roller thin strip casting process is specifically: the RKEF process is directly coupled with the stainless steel refining and thin strip continuous casting process, first, the burden of the RKEF furnace is calculated based on the target product demand using an intelligent burdening model, then the addition burden of the AOD furnace is cooperatively optimized and calculated based on the RKEF nickel molten iron composition using the intelligent burdening model (and the proportion and flow of the O2, Ar and N2 mixed gas are optimized in real time using a dynamic gas blowing control model), realizing the cost-optimal dynamic burdening under multiple constraints; the neural network algorithm GAN with physical constraint PI is used to predict the composition and temperature, and the predicted values of the composition and temperature and control instructions are output, the metallurgical physical law is embedded in the model training as a hard constraint, so that the control decision is both consistent with the data and in line with the scientific law, the process control is accurate, the overall process is more energy-saving, and the carbon dioxide (CO2) emission is reduced.

[0017] In addition to the purposes, features and advantages described above, the present application has other purposes, features and advantages. The present application will be further described below with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a schematic diagram of the intelligent stainless steel production method combined with RKEF smelting and double-roller thin strip casting process of the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative positional relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications also change accordingly.

[0022] In addition, the descriptions such as "first", "second" and the like in the present application are only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the technical features indicated, or implicitly indicating the number of the technical features indicated. Therefore, the features defined as "first", "second" can be explicitly or implicitly included at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly specified and limited.

[0023] In the present application, unless otherwise explicitly specified and limited, the terms "connection", "fixation" and the like should be understood broadly, for example, "fixation" can be fixed connection, or detachable connection, or integral; can be mechanical connection, or electrical connection; can be directly connected, or indirectly connected through intermediate medium, can be the internal communication of two elements or the interaction relationship of two elements, unless otherwise explicitly limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0024] In addition, the technical solutions of various embodiments of the present application can be combined with each other, but it must be based on the fact that a person skilled in the art can realize it, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor within the scope of protection required by the present application.

[0025] The present application discloses a method for producing stainless steel by combining RKEF smelting and double-roller thin strip casting process, which is described in detail in Figure 1 , comprising the following steps: First, based on the target product demand, the burden of the RKEF furnace is calculated by using an intelligent burdening model; the burden is mainly composed of laterite nickel ore and is supplemented with chromium ore, limestone, dolomite, quartzite, coke and coal. In this embodiment, the prepared burden is loaded into the RKEF system, dried and pre-reduced in the rotary kiln, and then the hot burden is sent into the electric arc furnace for high-temperature smelting to produce high-temperature low-grade nickel iron melt. This part of the process can refer to the prior art.

[0026] Second, the molten iron obtained in the first step is transferred to the AOD furnace through a ladle; an intelligent burdening model is used for burdening and collaborative optimization calculation; at least one of waste stainless steel, high-carbon chromium iron, nickel iron / nickel plate, flux and reducing agent is added for primary refining to obtain primary molten steel. Here, it also includes other alloy materials (selected according to actual needs). A dynamic gas blowing control model is used to optimize the proportion and flow of O2, Ar and N2 mixed gas in real time to carry out desiliconization, decarburization and phosphorus removal reactions to obtain primary molten steel.

[0027] In the present application, the intelligent batching model is a long short-term memory network model optimized by the Crown-Hog optimization algorithm, and the batching calculation includes the following steps: Step 2.1, collect data and create a data set, the input features of the data set are the target values of the target steel grades C, Si, Mn, P, S, Cr, Ni elements, the components of the raw materials (here the raw materials include furnace materials and batching materials), the components and weights of the RKEF molten iron; the output label is the proportion of each raw material. The preferred operation is: collect historical production data, obtain the standard limit and control range based on the target steel grade composition requirements (C, Si, Mn, P, S, Cr, Ni), the inventory and chemical composition data of each raw material, and the components and weights of the RKEF molten iron, and construct a data set for batching decision.

[0028] Step 2.2, pre-process the data including cleaning, normalization and missing value processing to obtain a high-quality data set. In the present application, the data set is preferably divided into training set and test set in the ratio of 7:3.

[0029] Step 2.3, initially select a long short-term memory network LSTM as an initial model; combine the high-quality data set and use the Crown-Hog optimization algorithm CPO to optimize the initial model to search for the optimal super parameter combination to obtain an improved hybrid model (i.e. intelligent batching model).

[0030] In the present application, the initially set network structure is 2-layer LSTM layer. The CPO algorithm simulates the defense and attack behavior of the Crown-Hog, generates multiple "candidate solutions" in the super parameter space (Hidden_size, Dropout_rate, Batch_size, Learning_rate, Lr_factor, Patience), uses these combinations to train the LSTM model, evaluates its performance, and then iteratively updates according to the fitness value, finally searches for the optimal super parameter combination, and finally obtains the improved hybrid model. The evaluation indicators of prediction error include the coefficient of determination (R 2 ), root mean square error (RMSE) and mean absolute percentage error (MAPE), when the prediction error R 2 of the improved hybrid model on the validation set reaches the first threshold, and the RMSE and MAPE are less than or equal to the second threshold and the third threshold, it means that the prediction accuracy and stability of the model meet the requirements. At this time, the training is terminated, and the improved hybrid model obtained not only performs well on the training data, but also has good generalization ability. Deployed to the batching calculation server online.

[0031] Step 2.4, the improved mixed model is used for calculation of ingredient calculation, and the required materials for ingredient and the corresponding amount are output. Specifically, when the production of a new heat of molten steel is carried out, the composition of the current target steel grade, the composition of the raw material used, the composition and weight of the RKEF molten iron are input, and the CPO-LSTM model calculates the optimal raw material ratio according to the input characteristics, and outputs the result; the actual final composition (spectrometer detection) of each heat of molten steel and the actual yield of each element are recorded, and the new data is stored in the database.

[0032] In the present application, the dynamic blowing control model is a decision model based on reinforcement learning, which dynamically adjusts the mixing ratio and flow of O2, Ar and N2 by real-time monitoring of furnace gas composition (mainly CO, CO2, O2), flue gas temperature, molten pool temperature and sound signal, and the optimization goal is to minimize the oxidation loss rate of chromium while reducing the carbon content to below the target value in the shortest time.

[0033] Step 3, the LF furnace receives the primary refined molten steel from the AOD furnace, and uses the neural network algorithm GAN with physical constraints (Physical Information, abbreviated as PI) to intelligently regulate the composition and temperature; after refining, refined molten steel is obtained. In this step: through arc heating, the temperature of the molten steel is uniformly and accurately adjusted to the casting temperature range required by the Twin-roll Strip Casting (TRSC) process; through argon stirring and slag refining, the composition is uniform, the inclusions are promoted to float, and the phosphorus reversion is prevented; according to the online rapid composition analysis result, the required alloy is added for accurate fine tuning of the composition. When the temperature and composition meet the standards, the molten steel is discharged and transferred to the tundish for TRSC thin strip casting.

[0034] The preferred step of the present application specifically includes: Step 3.1, the LF furnace refines the received molten steel.

[0035] Step 3.2, use the instrument assembly to obtain molten steel temperature data, three-phase electrode data, molten steel composition data and slag composition, and form a data set. In the present application, it is preferred to use an infrared thermometer and a thermocouple to obtain molten steel temperature data; use a voltage current transformer to obtain the voltage, current and power of the three-phase electrode; use an online spectrometer to obtain molten steel composition data; use an online slag detector to obtain slag composition, including CaO, SiO2, Al2O3, MgO, FeO, MnO and S. After obtaining the corresponding multi-source data, the data is preprocessed (including cleaning, normalization and missing value and outlier processing) to form a high-quality data set.

[0036] Step 3.3, the composition and temperature are predicted by the neural network algorithm GAN with physical constraints, and the predicted values of the composition and temperature and the control instructions are output. In the present application, the generator G is preferably used to predict the composition and temperature by the neural network algorithm GAN with physical constraints. The internal neural network model of the generator G learns a complex nonlinear mapping relationship from multi-source sensor data to predicted values and control instructions through training, and the training target is to make the predicted values as close to the true values as possible, and to make the control instructions effectively reduce the gap between the predicted values and the target values. The discriminator D receives the output of the generator G and calculates the physical loss by using the built-in physical constraint equation. The task of D is to judge whether the instruction of G is "physically reasonable". Through repeated adversarial training of G and D, G generates instructions that meet the target and comply with physical laws. In the neural network algorithm GAN with physical constraints, the metallurgical reaction kinetics equation is used as a loss function for physical constraints, as follows: ; ; ; ; ; wherein: , , is the constraint weight of adaptive adjustment; is the total physical loss term; is the energy conservation constraint term; is the mass transfer constraint term; is the slag-steel reaction constraint term; is the specific heat capacity of molten steel at constant pressure; m is the mass of molten steel in the ladle; is the change rate of the temperature of the molten pool; is the thermal efficiency of the LF furnace; is the arc voltage; is the arc current, is the power factor; is the total heat loss of the system; is the alloying element C, Si, Mn, P, S, Cr and Ni; is the change rate of the concentration of the element ; is the mass transfer coefficient of the element ; is the total surface area of the alloying material of the element ; is the density of the molten steel, is the saturation concentration of the element in the molten steel; is the element current concentration of sulfur; distribution ratio of sulfur; sulfur content in slag; sulfur content in molten steel; equilibrium constant of desulfurization reaction; activity of CaO in slag; activity coefficient of S in molten steel; activity of O in molten steel; content of P in molten steel; initial P content of molten steel; rate constant of rephosphorization reaction; time.

[0037] Step 3.4, judging the composition and temperature predicted in step 3.3, if the composition and temperature meet the standards, entering the fourth step; if the composition and temperature do not meet the standards, adding the required alloy for accurate fine-tuning of the composition and combining the control instructions, returning to step 3.1.

[0038] In the present application, the control instruction set is sent to the PID controller. The control instructions include: through the control of the alloy feeder, adding high-carbon chromium iron, low-carbon chromium iron, nickel iron, and molybdenum iron alloy for cost-optimal accurate fine-tuning; through the control of the argon regulating valve, optimizing the argon blowing flow to realize efficient stirring; through the control of the arc power of the electrode controller to control the temperature.

[0039] The fourth step, the refined molten steel obtained in the third step is injected into the flow distributor system of the TRSC through the tundish; the refined molten steel is obtained by double-roller casting to obtain the initial thin strip blank. That is, the molten steel is rapidly solidified in the molten pool formed by two high-speed rotating internal water-cooled cooling rollers, is rolled and drawn out at the roll gap of the two rollers, and forms the initial thin strip blank (which can refer to the existing thin strip continuous casting process).

[0040] The fifth step, the initial thin strip blank obtained in the fourth step is cooled to obtain a stainless steel thin strip. In the present application, the just-solidified thin strip blank is cooled through the gas mist cooling system according to the set cooling path; after cooling to the target coiling temperature, intelligent defect detection analysis of the thin strip is carried out at the outlet position, and finally the thin strip is coiled into a steel coil by the coiler.

[0041] In addition, the method further includes a sixth step, which is intelligent defect detection analysis of the thin strip, specifically including: Step 6.1, using an online visual detection system to obtain the defects and positions of the stainless steel thin strip; Step 6.2, introducing a defect quality comprehensive score as a recognition of the defect type, and quantifying the severity of the defect based on the defect quality comprehensive score obtained in step 6.2.

[0042] The preferred thin strip intelligent defect detection analysis is to collect the strip surface image through the online visual detection system deployed at the outlet. The image data is transmitted to the edge computing device in real time, and the optimized CNN model deployed therein is used for real-time analysis. The model needs to complete the inference of a single image within 50 ms to realize the classification and positioning of surface cracks, edge cracks, depressions, and vibration marks. The online visual detection system is equipped with a high-temperature-resistant (≥1400℃) dustproof protective cover and an adaptive light source, and the image acquisition frequency is not less than 100 frames / s; the defect quality comprehensive score is introduced into the optimized CNN model, and the optimized CNN model (i.e., the DefectCNN model) is deployed on the edge computing device with GPU acceleration, which can complete the analysis and defect classification of a single image within 50 ms. The optimized CNN model is a standard architecture composed of multiple layers of convolution, pooling, and full connection operations, but introduces a defect quality comprehensive score (D) as the basis for identifying the defect type and quantifying the severity. ).

[0043] The defect quality comprehensive score in the application is calculated as follows: ; ; Wherein: D is the defect quality comprehensive score; is the defect category index, wherein 1 is an edge crack, 2 is a subsurface porosity, 3 is a vibration mark, and 4 is a depression; is the total number of defect categories, is the weight coefficient; is the probability value of the model output considering it as the th defect category; is a self-defined function for calculating the defect severity; represents the physical characteristics of the defect.

[0044] The self-defined function for calculating the defect severity in the application is as follows: ; ; ; ; Wherein: is the self-defined function of crack severity; crack_length is the crack length; L_critical is the critical length threshold; is the self-defined function of subsurface porosity severity; Avg_diameter_porosity is the average diameter of the porosity; D_porosity_critical is the critical threshold of the diameter; is a user-defined function of the severity of the oscillation; max_depth_oscillation is the maximum depth of the oscillation; D_oscillation_critical is the critical threshold of the depth of the oscillation; is a user-defined function of the severity of the concave; Depth_concave is the depth of the concave; D_critical_concave is the critical threshold of the depth of the concave; Area_concave is the area of the concave; A_critical_concave is the critical threshold of the area of the concave.

[0045] In the present application, the system hierarchical response mechanism is when the defect quality comprehensive score S total is lower than the confidence L1, the system only records data; when S total is between the confidence L1 and L2, the system automatically calls the PLC execution mechanism to fine-tune the process parameters; when S total exceeds the confidence L2, the system triggers a high-level alarm and submits control suggestions to the operator for final decision confirmation, realizing intelligent production of man-machine cooperation.

[0046] In the present application, according to the output defect type and score, the hierarchical response mechanism based on confidence generates an optimized control instruction set, thereby constructing an intelligent stainless steel production system of "raw material-melting-rolling-quality" full-process integration, data-driven, and self-learning optimization.

[0047] The technical scheme of the present application has the following effects: the core of the present application is to construct an intelligent stainless steel production system of "raw material-melting-rolling-quality" full-process integration, data-driven, and self-learning optimization. Creatively, the RKEF process is directly coupled with the stainless steel refining and thin strip continuous casting process. The CPO-LSTM model is adopted to realize the cost-optimal dynamic proportioning under multiple constraints. The PI-GAN model is adopted to embed the metallurgical physical law as a hard constraint into the model training, so that the control decision not only fits the data but also conforms to the scientific law, and precise process control is realized. The DefectCNN model is adopted to not only identify defects but also innovatively define a defect quality comprehensive score to quantify the defect severity, thereby providing a basis for intelligent decision-making.

[0048] Application case: Take 70 tons of laterite nickel ore as the main raw material, add 5 tons of chromium ore, 8 tons of limestone, 4 tons of dolomite, 2 tons of quartz stone, 7.5 tons of coke, and 3.5 tons of coal. The prepared furnace charge is loaded into the RKEF system. First, dry and pre-reduce in the rotary kiln, then send the hot charge to the submerged arc furnace for high-temperature smelting. Output high-temperature low-grade nickel iron melt, composition includes: Ni 9.5%, Cr 2.5%, C 2.0%, Si 1.5%, Mn 1.2%, P 0.03%, S 0.05%, Fe balance, temperature 1450℃.

[0049] The high-temperature nickel iron melt produced by RKEF is directly hot charged into the AOD furnace through the ladle. Using scrap stainless steel, high-carbon chromium iron, nickel iron / nickel plate, other alloy elements, flux, and reducing agent as raw materials, intelligent raw material batching is used to adjust the final composition. In the AOD furnace, O2, Ar, and N2 mixed gas is blown in to carry out desiliconization, decarburization, chromium preservation, and dephosphorization reactions. When the C and P contents meet the requirements, the molten steel is transferred to the ladle.

[0050] Collect historical production data to obtain the standard limits and control ranges based on the target steel composition requirements (C, Si, Mn, P, S, Cr, Ni) (as shown in Table 1), the inventory and chemical composition data of each raw material, and the composition and weight of the RKEF molten iron, to build the data basis for batching decision-making.

[0051] Table 1 Target steel composition control range (unit: wt%)

[0052] Create a dataset, the input features of the dataset are the target values of the target steel C, Si, Mn, P, S, Cr, and Ni elements, and the composition of the furnace charge and batching (as shown in Tables 2 and 3), and the composition and weight of the RKEF molten iron. The output label is the ratio of each raw material; Table 2 Composition of available furnace charge (unit: wt%)

[0053] Table 3 Composition of available batching (unit: wt%)

[0054] Clean, normalize, and handle missing values of the data to form a high-quality dataset. Divide the training set and test set in a ratio of 7:3.

[0055] The hybrid model of long short-term memory network (LSTM) (i.e., intelligent batching model) is optimized by Crested Porcupine Optimizer (CPO) for batching calculation. The initial network structure of CPO-LSTM model is set as 2-layer LSTM layer. The CPO algorithm simulates the defense and attack behavior of Crested Porcupine, generates multiple "candidate solutions" in the hyperparameter space (Hidden_size[32, 512], Dropout_rate[0.1, 1.0], Batch_size[16, 256], Learning_rate[0.0001, 0.01], Lr_factor[0.1, 1.0], Patience[1, 10]), uses these combinations to train the LSTM model, evaluates its performance, and then iteratively updates according to the fitness value. Finally, the optimal hyperparameter combination is searched as follows: Hidden_size1=184; Hidden_size2=78; Dropout_rate=0.015; Batch_size=32; Learning_rate=0.012; Lr_factor=0.33; Patience=8.

[0056] The evaluation indicators of prediction error include coefficient of determination (R 2 ), root mean square error (RMSE) and mean absolute percentage error (MAPE); when the prediction error of CPO-LSTM model on the validation set R 2 ≥0.93 (first threshold), RMSE≤0.015 (second threshold) and MAPE≤2% (third threshold), it indicates that the prediction accuracy and stability of the model meet the requirements. After this training, the performance of the model on the validation set is: R²=0.955, RMSE=0.012, MAPE=1.97%, the training is terminated, and the obtained CPO-LSTM model not only performs well on the training data, but also has good generalization ability.

[0057] When batching for producing a new furnace of molten steel, the system inputs the composition of the current target steel grade, the composition of the used raw materials, the composition and weight of RKEF molten iron, and the CPO-LSTM model calculates the optimal raw material ratio according to these input features to meet the requirements as follows: Laterite nickel ore: 65.7 tons; Chromium ore: 4.7 tons; Limestone: 7.5 tons; Dolomite: 3.7 tons; Quartzite: 1.9 tons; Coke: 7 tons; Coal: 3 tons; RKEF hot metal: 38 tons; Scrap stainless steel: 73.8 tons; High-carbon ferrochrome: 7.4 tons; Nickel plate: 1.2 tons.

[0058] The dynamic blowing control model dynamically decides and outputs adjustment instructions for the blowing scheme according to the real-time monitored furnace gas composition (CO: 15%, CO2: 5%, O2: 1.5%), flue gas temperature (1650°C), and molten pool temperature (1680°C) through a reinforcement learning algorithm. The blowing process is divided into a decarburization and chromium preservation period and a reduction period: in the decarburization and chromium preservation period, the model controls the O2 flow to be adjusted within the range of 1200-1500 Nm³ / h, and a certain proportion of Ar gas (230 Nm³ / h) is mixed. In the reduction period, when the carbon content decreases to the vicinity of the target value, the model greatly reduces the O2 flow and closes the O2, increases the Ar gas flow (350 Nm³ / h) for stirring, and can inject a small amount of N2 (50 Nm³ / h) for composition control or cooling according to the situation. At the same time, the model controls the addition of ferrosilicon and other reducing agents to reduce chromium oxide. Through this dynamic control, the carbon content is reduced from the initial 2.0% to below 0.05% in 15 minutes, and the oxidation loss rate of chromium is controlled within 1.5%.

[0059] The actual final composition of the molten steel of each heat (spectrum detector: C 0.05%, Si 0.25%, Mn 1.18%, P 0.032%, S 0.018%, Cr 18.35%, Ni 8.15%) and the actual yield of each element (Cr: 98.5%, Ni: 99.2%) are recorded, and this new data is stored in the database.

[0060] The high-temperature infrared thermometer and the continuous temperature thermocouple are used to obtain the molten steel temperature data. The high-precision voltage and current transformer is used to obtain the voltage (U=250V), current (I=45kA), and power (P=10 MW) data of the three-phase electrode. The online spectrometer is used to obtain the molten steel composition data (C 0.052%, Si 0.28%, Mn 1.18%, P 0.031%, S 0.018%, Cr 18.35%, Ni 8.15%). The slag online detector is used to obtain the slag composition (CaO=55%, SiO2=20%, Al2O3=10%, MgO=8%, FeO=0.8%, S=0.8%).

[0061] After receiving the pre-processed high-quality dataset, the generator G outputs a set of preliminary prediction values ([C]=0.05%, [Si]=0.28%, [Mn]=1.18%, [P]=0.031%, [S]=0.018%, [Cr]=18.48%, [Ni]=8.15%, T pred =1545℃) and preliminary control instructions. The control instructions include: the feeding speed of the low-carbon chromium iron feeder is 50 kg / min, the feeding amount of the calcium carbide feeder is 50 kg, the argon flow of the argon control valve is 100 NL / min, and the arc power of the electrode controller is 9.5 MW.

[0062] The discriminator D receives the output of the generator G and calculates the physical loss using the built-in physical constraint equation. The task of D is to judge whether the instructions of G are "physically reasonable". In this calculation, the thermal efficiency =0.72; the sulfur distribution ratio =44.4. Through repeated adversarial training of G and D, G generates instructions that meet the target and conform to the physical law.

[0063] The optimized control instruction set is sent to the PID controller. By controlling the alloy feeder, 200 kg of low-carbon chromium iron is added for cost-optimal precise fine-tuning; by controlling the argon regulating valve, the argon flow is optimized to achieve efficient stirring; by controlling the slag feeder, 20 kg of calcium carbide is added to make "white slag"; by controlling the arc power of the electrode controller, the temperature is controlled to 9.5 MW; when the temperature is uniformly reached 1550℃, the composition is fine-tuned to [C]=0.049%, [Si]=0.58%, [Mn]=1.21%, [P]=0.03%, [S]=0.015%, [Cr]=18.5% and [Ni]=8.2%, the molten steel is tapped and transferred to the tundish.

[0064] The online visual detection system is equipped with a high-temperature-resistant (≥1400℃) dustproof protective cover and an adaptive light source, and the image acquisition frequency is not less than 100 frames / second; the optimized CNN model is deployed on a GPU-accelerated edge computing device, which can complete the analysis and defect classification of a single image within 50ms. The hierarchical response mechanism of the system is that when the defect quality comprehensive score is below the confidence L1=0.05, the system only records data; when it is between the confidence L1=0.05 and L2=0.20, the system automatically calls the PLC executive mechanism to fine-tune the process parameters; when it exceeds the confidence L2=0.20, the system triggers a high-level alarm and submits control suggestions to the operator for final decision confirmation, realizing intelligent production of man-machine cooperation.

[0065] The PLC execution mechanism comprises a hydraulic servo system, an air mist cooling system, a cooling roller control system, a ladle pouring system and a curling system.

[0066] The offline detection results of the final product, such as thickness, plate shape, mechanical properties and metallographic structure (thickness 2.25 mm, yield strength 280 MPa, tensile strength 620 MPa, elongation 55%; metallographic structure: austenite + 5% delta ferrite), are transmitted to the self-learning training module to automatically optimize the control model, and the online control model is continuously improved and optimized through incremental learning combined with real-time production data.

[0067] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of intelligent production of stainless steel combining RKEF smelting and twin roll thin strip casting process, characterized in that, The method comprises the following steps: The first step is to calculate the burden of the RKEF furnace based on the requirements of the target product by using an intelligent burdening model, to load the prepared burden into the RKEF system, and to smelt nickel molten iron with controllable composition and temperature; The second step is to hot charge the nickel molten iron obtained in the first step into an AOD furnace through a molten iron ladle; based on the composition of the RKEF nickel molten iron, the burden added to the AOD furnace is calculated and optimized by using the intelligent burdening model, and the proportion and flow rate of the mixed gas of O2, Ar and N2 are optimized in real time by using a dynamic gas blowing control model, so as to carry out desiliconization, decarburization, chromium preservation and dephosphorization reactions, and obtain primary refined molten steel; The third step is to receive the primary refined molten steel from the AOD furnace by using an LF furnace, and to intelligently control the composition, gas blowing and temperature by using a neural network algorithm with physical constraints (GAN); After the refining is completed, refined molten steel is obtained, which specifically comprises: Step 3.1, the LF furnace refines the received molten steel; Step 3.2, an instrument assembly is used to obtain molten steel temperature data, three-phase electrode data, molten steel composition data and slag composition, so as to form a data set; Step 3.3, the neural network algorithm with physical constraints (GAN) is used to predict the composition and temperature, and the predicted values of the composition and temperature and control instructions are outputted; Step 3.4, the composition and temperature predicted in step 3.3 are judged, if the composition and temperature meet the requirements, the fourth step is entered, if the composition and temperature do not meet the requirements, the required alloy is added for accurate fine adjustment of the composition and the control instructions are combined, and step 3.1 is returned to; The fourth step is to inject the refined molten steel obtained in the third step into a flow distributor system of a double-roller thin strip continuous casting through a tundish; the refined molten steel is cast by a double-roller to obtain an initial thin strip blank; The fifth step is to cool the initial thin strip blank obtained in the fourth step to obtain a stainless steel thin strip.

2. The method of intelligent production of stainless steel incorporating RKEF melting and twin roll thin strip casting process as claimed in claim 1 wherein, The burden is obtained by taking laterite nickel ore as the main raw material and adding chromium ore, limestone, dolomite, quartzite, coke and coal; the burden includes at least one of waste stainless steel, high-carbon chromium iron, nickel iron / nickel plate, flux and reducing agent.

3. The method of intelligent production of stainless steel incorporating RKEF melting and twin roll thin strip casting process as claimed in claim 1 wherein, The dynamic gas blowing control model is a decision model based on reinforcement learning, which dynamically adjusts the mixing ratio and flow rate of O2, Ar and N2 by real-time monitoring of furnace gas composition, flue gas temperature, molten pool temperature and sound signals.

4. The method of intelligent production of stainless steel incorporating RKEF melting and twin roll thin strip casting process as claimed in claim 1 wherein, The intelligent burdening model is a long short-term memory network model optimized by the CPO optimization algorithm; The calculation of the intelligent burdening model comprises the following steps: Step 2.1, collect data and create a data set, specifically: the input features of the data set are the target values of the C, Si, Mn, P, S, Cr and Ni elements of the target steel, the composition of the raw materials used, the composition and weight of the RKEF molten iron; the output label is the proportion of each raw material; Step 2.2, pre-process the data including cleaning, normalization and missing value processing to obtain a high-quality data set; Step 2.3, initially select a long short-term memory network (LSTM) as an initial model; combine the high-quality data set to search for the optimal super parameter combination of the initial model by using the CPO optimization algorithm to obtain an intelligent burdening model; Step 2.4, calculate the burden by using the intelligent burdening model, and output the required substances and corresponding amounts of the raw materials.

5. The method of intelligent production of stainless steel incorporating RKEF melting and twin roll thin strip casting process as claimed in claim 1 wherein, In step 3.2: the temperature data of the molten steel is obtained by using an infrared temperature measuring instrument and a thermocouple; the voltage, current and power of the three-phase electrode are obtained by using a voltage and current transformer; the composition data of the molten steel is obtained by using an online spectrometer; and the composition of the slag, including CaO, SiO2, Al2O3, MgO, FeO, MnO and S, is obtained by using an online slag detector.

6. The method of intelligent production of stainless steel incorporating RKEF melting and twin roll thin strip casting process as claimed in claim 1 wherein, In the neural network algorithm GAN with physical constraints in step 3.3, the metallurgical reaction kinetics equation is used as a loss function for physical constraints, as follows: ； ； ； ； ； wherein: , , is the constraint weight of adaptive adjustment; is the total physical loss term; is the energy conservation constraint term; is the mass transfer constraint term; is the slag-steel reaction constraint term; is the specific heat capacity of the molten steel at constant pressure; m is the mass of the molten steel in the ladle; is the rate of change of the bath temperature; is the thermal efficiency of the LF furnace; is the arc voltage; is the arc current, is the power factor; is the total heat loss of the system; are the alloying elements C, Si, Mn, P, S, Cr, and Ni; is the concentration of element ; is the mass transfer coefficient of element ; is the total surface area of the alloying elements ; is the density of the molten steel, is the saturation concentration of element in the molten steel; is the current concentration of element ; is the sulfur partition ratio; is the sulfur content in the slag; is the sulfur content in the molten steel; is the equilibrium constant of the desulfurization reaction; is the activity of CaO in the slag; is the activity coefficient of S in the molten steel; is the activity of O in the molten steel; is the content of P in the molten steel; is the initial P content in the molten steel; is the rate constant of the rephosphorization reaction; is time.

7. The method of intelligent production of stainless steel combining RKEF smelting and twin roll thin strip casting process as claimed in claim 6 wherein, The control instructions in step 3.4 include: the feeding speed of the corresponding feeding machine for low-carbon ferrochrome, ferronickel and ferromolybdenum; the feeding amount of the corresponding feeding machine for calcium carbide and aluminum particles; the argon blowing flow of the argon control valve; and the arc power of the electrode controller.

8. The method of intelligent production of stainless steel combining RKEF smelting and twin roll strip casting process as claimed in any one of claims 1 to 7, wherein, The sixth step, which is thin strip intelligent defect detection and analysis, includes the following steps: Step 6.1: obtaining the defects and positions of the stainless steel thin strip by using an online visual detection system; Step 6.2: introducing a defect quality comprehensive score as a recognition of the defect type, and quantifying the severity of the defect based on the obtained defect quality comprehensive score.

9. The method of intelligent production of stainless steel incorporating RKEF melting and twin roll thin strip casting process as claimed in claim 8 wherein, The defect quality comprehensive score in step 6.2 is calculated as follows: ； ； wherein: is the defect quality comprehensive score; is the defect category index, wherein: 1 is edge crack, 2 is subsurface porosity, 3 is shake mark, 4 is indentation; is the total number of defect categories; is the weight coefficient; is the probability value considered by the model to be the category defect; is a self-defined function for calculating defect severity; represents the physical characteristics of the defect.

10. The method of intelligent production of stainless steel incorporating RKEF melting and twin roll thin strip casting process as claimed in claim 9 wherein, The self-defined function for calculating the defect severity is as follows: The self-defined function for calculating the defect severity is as follows: ； ； ； ； wherein: is a custom function for crack severity; crack_length is the crack length; L_critical is the critical length threshold; is a custom function for sub-surface porosity severity; Avg_diameter_porosity is the average diameter of the porosity; D_porosity_critical is the critical threshold for diameter; is a custom function for oscillation severity; max_depth_oscillation is the maximum depth of the oscillation; D_oscillation_critical is the critical threshold for oscillation depth; is a custom function for concave severity; Depth_concave is the depth of the concave; D_critical_concave is the critical threshold for concave depth; Area_concave is the area of the concave; A_critical_concave is the critical threshold for concave area.

Images