Smelting and rolling integrated process for ultra-pure ferritic stainless steel

Abstract

The invention provides a smelting and rolling integrated process of ultra-pure ferritic stainless steel, which comprises a series of steps of scrap preheating, smelting, refining, continuous casting, hot rolling, cold rolling, annealing, pickling and the like, and is combined with online monitoring, nondestructive testing and machine learning algorithms to realize the whole-flow integrated control from smelting to rolling. The problems of high energy consumption and low efficiency in the traditional separation process are solved, and the method has the advantages of improving the production efficiency, reducing the energy consumption cost and realizing accurate control and rapid adjustment.

Description

Technical Field

[0001] The present invention relates to the field of preparation of ultra-pure ferritic stainless steel, and particularly to a smelting and rolling integrated process for ultra-pure ferritic stainless steel. Background Art

[0002] The preparation process of ultra-pure ferritic stainless steel includes smelting and rolling. Traditionally, these two processes are carried out separately and independently. The core of ultra-pure ferritic stainless steel smelting lies in the control of extremely low C and N contents. In the early stage, the three-step method (electric arc furnace + AOD / VOD vacuum refining) was the mainstream. In recent years, enterprises have significantly improved the decarburization and denitrification efficiency by improving vacuum refining equipment (such as VOD, SSVOD, VCR, etc.) and process parameters. Domestic enterprises such as Baosteel and Taigang have broken through key technologies such as vacuum smelting accuracy and continuous casting furnace number through continuous research. Baosteel achieved a year-on-year increase of 55.7% in the production capacity of ultra-pure ferritic stainless steel in 2013, and improved the quality stability through process innovation (such as "Optimizing the Refining Process of Ultra-Pure Ferritic Stainless Steel"). Taigang adopted the AODVCR process, combined with vacuum and strong stirring technologies, to reduce the nitrogen content to an extremely low level (20 - 90×10 -6 ).

[0003] In terms of rolling, the rolling process of ultra-pure ferritic stainless steel is usually carried out on a cold tandem rolling production line for stainless steel, aiming to roll the steel billets obtained from smelting into ultra-thin strip materials. However, this separate smelting and rolling process has problems of high energy consumption and low efficiency.

[0004] Recently, the smelting and rolling integrated process of ultra-pure ferritic stainless steel has begun to come into the view of the industry. Enterprises have tried to reduce intermediate cooling and reheating steps by integrating process parameters in the smelting and rolling links (such as hot rolling temperature control, direct rolling of continuous casting billets), so as to reflect the advantages of synergy between smelting and rolling. This integrated method is expected to significantly improve production efficiency, reduce energy consumption and costs.

[0005] However, the current integrated process still has many challenges. First, it is difficult to coordinate and optimize the parameters of the smelting and rolling processes, and precise control of the entire process from melting to finished products is required. Second, the real-time monitoring and quality control technologies in the integrated process need to be improved, especially in the production environment of high temperature, high pressure and high speed. Third, the existing equipment and processes are difficult to meet the strict requirements of ultra-pure ferritic stainless steel for extremely low carbon and nitrogen contents. Finally, the automation and intelligent level of the integrated production line is not high enough to achieve precise control and rapid adjustment of the production process.

[0006] In view of the above problems, the existing technology urgently needs to be improved. Summary of the Invention

[0007] To solve the above technical problems, the object of the present invention is to provide an integrated smelting and rolling process for ultra-pure ferritic stainless steel, which has the advantages of improving production efficiency, reducing energy consumption costs, achieving precise control and rapid adjustment.

[0008] To solve the above technical problems, the present invention adopts the following technical solutions:

[0009] An integrated smelting and rolling process for ultra-pure ferritic stainless steel, the technical solution is as follows: It includes the following steps: Scrap steel is preheated to 600 - 700 °C in a quantum arc furnace by an alternating electromagnetic field, and then electrified to melt, controlling the melting temperature and time; In the AOD refining stage, Ar / N mixed gas is introduced, the stirring intensity is ≥ 1000 L / min, and the carbon content is controlled ≤ 0.005%; In the VOD vacuum refining stage, the vacuum degree is maintained ≤ 30 Pa, and decarburization is carried out until C + N ≤ 0.01%; In the continuous casting process, an electromagnetic stirring crystallizer is used, the superheat of the molten steel is ≤ 20 °C, the thickness of the continuous casting billet is 200 - 250 mm, and the proportion of equiaxed crystals is ≥ 50%; In the hot rolling process, the thickness of the intermediate billet in rough rolling is 30 - 50 mm, the finishing rolling exit temperature is 780 - 820 °C, and the coiling temperature is 550 - 650 °C; In the cold rolling process, a three-stage gradient roll is used, and the rolling force is reduced by 8 - 12% per pass; The double annealing process includes recrystallization annealing and secondary annealing. Among them, the temperature of recrystallization annealing is 850 - 950 °C, the annealing time is 5 - 8 min, the temperature of secondary annealing is 700 - 750 °C, and the annealing time is 10 - 15 min; Pickling is carried out using a nitric acid and hydrofluoric acid mixed solution with a volume ratio of 4:1 - 2:1, and the pickling time is 10 - 30 minutes; Collect, store and analyze the production data of on-line monitoring and non-destructive testing; Use machine learning algorithms to perform in-depth learning on the production data to discover potential rules and problems; Feed the data back to the control system to adjust the production parameters in real time to achieve automatic and intelligent control of the production process.

[0010] Furthermore, the present application also proposes that the quantum arc furnace includes: An alternating electromagnetic coil is arranged in the furnace cavity, with a frequency of 10 - 100 kHz and a magnetic field intensity ≥ 5 T; The scrap steel preheating area is separated from the melting area, and the temperature gradient in the preheating area is ≤ 50 °C / m.

[0011] Furthermore, the present application also proposes that on-line monitoring includes using laser-induced breakdown spectroscopy to monitor the content of carbon, nitrogen, chromium, and molybdenum elements in molten steel in real time, and using machine vision to monitor the surface quality of hot-rolled plates and cold-rolled plates in real time.

[0012] Furthermore, the present application also proposes that non-destructive testing includes using an ultrasonic flaw detector to detect cracks, pores, and inclusion defects inside steel billets and steel plates.

[0013] Furthermore, this application also proposes that in the above steps, it further includes cleaning, filtering, and denoising the collected data to eliminate outliers and interference signals.

[0014] Furthermore, this application also proposes that in the above steps, the machine learning algorithm includes predicting the production status within a certain period of time in the future based on the process model and the current state, and adjusting the parameters in advance to achieve preventive control.

[0015] Furthermore, this application also proposes that in the AOD refining stage, the ratio of Ar / N mixed gas is 80:20, and a two-stage spray gun structure is adopted, with the argon spray gun and the nitrogen spray gun working alternately.

[0016] Furthermore, this application also proposes that in the continuous casting process, segmented cooling is adopted in the secondary cooling zone, with a specific water ratio of 0.2 - 0.4 L / kg, a casting speed of 0.6 - 1.4 m / min, an electromagnetic stirring current of 200 - 400 A in the mold, and a frequency of 1 - 4 Hz.

[0017] Furthermore, this application also proposes that after pickling, electrolytic polishing treatment is adopted, with a current density of 5 - 20 A / dm 2 , the pH value of the electrolyte is 2 - 3, the polishing time is 5 - 15 minutes, and the surface roughness Ra ≤ 0.05 μm.

[0018] Furthermore, this application also proposes that in the VOD vacuum refining stage, a calcium treatment process is added. In the calcium treatment, the calcium content of the Al - Ca alloy is 6 - 10 wt%, the addition amount is 0.08 - 0.15% of the mass of the molten steel, and it is added in two times.

[0019] As can be seen from the above, a smelting and rolling integrated process for ultra - pure ferritic stainless steel provided by this application includes a series of steps such as scrap pre - heating, melting, refining, continuous casting, hot rolling, cold rolling, annealing, pickling, etc. Combining on - line monitoring, non - destructive testing, and machine learning algorithms, it realizes the full - process integrated control from smelting to rolling, solves the problems of high energy consumption and low efficiency existing in traditional separation processes, and has the advantages of improving production efficiency, reducing energy consumption costs, achieving precise control, and rapid adjustment. Description of the Drawings

[0020] Figure 1 It is the process flow chart of a smelting and rolling integrated process for an ultra - pure ferritic stainless steel of the present invention;

[0021] Figure 2 It is the control flow chart of a smelting and rolling integrated process for an ultra - pure ferritic stainless steel of the present invention. Detailed Embodiments

[0022] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0023] In the description of the present invention, it should be understood that if there are terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., the orientation or positional relationship indicated is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0024] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "mounted", "connected", and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection. It may be a mechanical connection or an electrical connection. It may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] As Figure 1-2 shown, the smelting and rolling processes of ultra-pure ferritic stainless steel have traditionally been carried out separately. The smelting process mainly focuses on controlling extremely low carbon and nitrogen contents, while the rolling process is carried out on a cold tandem rolling production line for stainless steel. The traditional smelting process mainly uses an electric arc furnace + AOD / VOD vacuum refining as the mainstream. In recent years, by improving the vacuum refining equipment and process parameters, the decarburization and denitrification efficiency has been significantly improved. However, the integration of smelting and rolling in the prior art has not been effectively verified in practice.

[0026] During the smelting process, scrap steel is preheated to 600 - 700 °C in a quantum arc furnace by an alternating electromagnetic field and then melted by power supply, controlling the smelting temperature and time. In the AOD refining stage, an Ar / N mixed gas is introduced, the stirring intensity is ≥1000 L / min, and the carbon content is controlled ≤0.005%. In the VOD vacuum refining stage, the vacuum degree is maintained ≤30 Pa, and the decarburization is carried out until C + N ≤0.01%. In the continuous casting process, an electromagnetic stirring crystallizer is used, the superheat of the molten steel is ≤20 °C, the thickness of the continuous casting billet is 200 - 250 mm, and the proportion of equiaxed crystals is ≥50%. In the hot rolling process, the thickness of the intermediate billet in rough rolling is 30 - 50 mm, the finishing rolling exit temperature is 780 - 820 °C, and the coiling temperature is 550 - 650 °C. In the cold rolling process, a three - level gradient roll is used, and the rolling force is reduced by 8 - 12% for each pass. The double - annealing process includes recrystallization annealing and secondary annealing. The temperature of recrystallization annealing is 850 - 950 °C and the annealing time is 5 - 8 minutes. The temperature of secondary annealing is 700 - 750 °C and the annealing time is 10 - 15 minutes. Pickling is carried out using a mixed solution of nitric acid and hydrofluoric acid with a volume ratio of 4:1 - 2:1, and the pickling time is 10 - 30 minutes. Various production data of on - line monitoring and non - destructive testing are collected, stored and analyzed. Machine learning algorithms are used to perform deep learning on the production data to discover potential laws and problems. The data is fed back to the control system to adjust the production parameters in real time, realizing the automatic and intelligent control of the production process.

[0027] During the smelting process, scrap steel is preheated to 600 - 700°C in a quantum arc furnace by an alternating electromagnetic field and then melted by power supply. The melting temperature and time are controlled, which can effectively preheat the scrap steel and improve the melting efficiency. In the AOD (argon-oxygen decarburizing, a furnace type similar to a side-blown converter, where a mixture of argon and oxygen with different proportions is blown into the molten pool from the bottom side of the furnace to reduce POO in the bubbles and oxidize the carbon in the steel, while the chromium in the steel is not easily oxidized) refining stage, Ar / N mixed gas is introduced, the stirring intensity is ≥1000 L / min, and the carbon content is controlled ≤0.005%. In this stage, the carbon content is controlled through gas stirring and refining to ensure the purity of the molten steel. In the VOD (Vacuum Oxygen Decarburization, which reduces oxides and carbides in the molten steel to gases in a vacuum environment to achieve the purpose of decarburization and deoxidation) vacuum refining stage, the vacuum degree is maintained ≤30 Pa, and the decarburization is carried out until C+N ≤0.01%. Through refining in a vacuum environment, the carbon and nitrogen contents in the molten steel are further reduced. In the continuous casting process, an electromagnetic stirring crystallizer is used, the superheat of the molten steel is ≤20°C, the thickness of the continuous casting billet is 200 - 250 mm, and the proportion of equiaxed crystals is ≥50%. Through electromagnetic stirring and control of the superheat, the quality and uniformity of the casting billet are improved. In the hot rolling process, the thickness of the intermediate billet in rough rolling is 30 - 50 mm, the finishing rolling exit temperature is 780 - 820°C, and the coiling temperature is 550 - 650°C. By controlling the temperature and thickness in the hot rolling process, the rolling quality is ensured. In the cold rolling process, a three-stage gradient roll is used, and the rolling force is reduced by 8 - 12% step by step. By gradually reducing the rolling force, the defects generated during the rolling process are reduced. The double annealing process includes recrystallization annealing and secondary annealing. The temperature of recrystallization annealing is 850 - 950°C and the annealing time is 5 - 8 minutes. The temperature of secondary annealing is 700 - 750°C and the annealing time is 10 - 15 minutes. Through the double annealing process, internal stresses are eliminated and the material properties are improved. Pickling is carried out using a mixed solution of nitric acid and hydrofluoric acid with a volume ratio of 4:1 - 2:1, and the pickling time is 10 - 30 minutes. Through pickling, the surface oxide layer and impurities are removed. The production data of on-line monitoring and non-destructive testing are collected, stored and analyzed. Through real-time monitoring and data analysis, the stability of the production process is ensured. Machine learning algorithms are used to perform deep learning on the production data to discover potential rules and problems. Through machine learning, the production parameters are optimized. The data is fed back to the control system to adjust the production parameters in real time, realizing the automation and intelligent control of the production process. Through the feedback control system, the optimization and automation of the production process are achieved.

[0028] Specifically, scrap steel is preheated to 600 - 700°C in a quantum arc furnace through an alternating electromagnetic field, and then electrified for melting. The smelting temperature and time are controlled to ensure the effective preheating and melting efficiency of the scrap steel. In the AOD refining stage, by introducing an Ar / N mixed gas and achieving a stirring intensity of ≥1000 L / min, the carbon content is controlled to ≤0.005%, ensuring the purity of the molten steel. In the VOD vacuum refining stage, the vacuum degree is maintained at ≤30 Pa, and the carbon is decarburized to C + N ≤0.01%, further reducing the carbon and nitrogen content in the molten steel. In the continuous casting process, an electromagnetic stirring crystallizer is used to control the superheat of the molten steel to ≤20°C, the thickness of the continuous casting billet is 200 - 250 mm, and the proportion of equiaxed crystals is ≥50%, improving the quality and uniformity of the billet. In the hot rolling process, the thickness of the intermediate billet in rough rolling is controlled at 30 - 50 mm, the finishing mill exit temperature is 780 - 820°C, and the coiling temperature is 550 - 650°C, ensuring the rolling quality. In the cold rolling process, a three - stage gradient roll is used, and the rolling force is reduced by 8 - 12% per pass, reducing the defects generated during rolling. The two - stage annealing process includes recrystallization annealing and secondary annealing. The recrystallization annealing temperature is 850 - 950°C and the annealing time is 5 - 8 minutes. The secondary annealing temperature is 700 - 750°C and the annealing time is 10 - 15 minutes, eliminating internal stress and improving the material properties. Pickling is carried out using a mixed solution of nitric acid and hydrofluoric acid with a volume ratio of 4:1 - 2:1, and the pickling time is 10 - 30 minutes to remove the surface oxide layer and impurities. Through on - line monitoring and non - destructive testing, various production data are collected, stored, and analyzed to ensure the stability of the production process. Machine learning algorithms are used to perform deep learning on the production data, discover potential laws and problems, and feed the data back to the control system to adjust the production parameters in real time, realizing the automated and intelligent control of the production process.

[0029] Compared with the prior art, by integrating the process parameters of the smelting and rolling links, reducing the intermediate cooling and reheating steps, the present application significantly improves the production efficiency and product quality. By adopting a quantum arc furnace to preheat scrap steel, AOD refining, VOD vacuum refining, an electromagnetic stirring crystallizer, a three - stage gradient roll, a two - stage annealing process, pickling, on - line monitoring and non - destructive testing, machine learning algorithms, and an automated control system, efficient coordination is achieved among various process links, ensuring the high - quality production of super - pure ferritic stainless steel.

[0030] Through preheating and melting scrap steel in a quantum arc furnace, gas stirring and refining in the AOD refining stage, vacuum environment refining in the VOD vacuum refining stage, electromagnetic stirring and superheat control in the continuous casting process, temperature and thickness control in the hot rolling process, gradually reducing the rolling force in the cold rolling process, eliminating internal stress in the double annealing process, removing the surface oxide layer and impurities in pickling, real-time data collection and analysis in on-line monitoring and non-destructive testing, deep learning and optimizing production parameters in machine learning algorithms, and real-time adjustment of production parameters in the automated and intelligent control system, an integrated process for smelting and rolling ultra-pure ferritic stainless steel is finally achieved, improving production efficiency and product quality.

[0031] Furthermore, this application also proposes that the quantum arc furnace includes an alternating electromagnetic coil arranged in the furnace cavity, with a frequency of 10 - 100 kHz and a magnetic field strength ≥ 5 T; the scrap steel preheating area is separated from the melting area, and the temperature gradient in the preheating area ≤ 50 °C / m.

[0032] By setting an alternating electromagnetic coil and applying an electromagnetic field with a frequency between 10 - 100 kHz and a magnetic field strength ≥ 5 T, the scrap steel can be efficiently preheated and melted. The separation design of the scrap steel preheating area and the melting area enables the temperature gradient in the preheating area ≤ 50 °C / m, ensuring a uniform and stable preheating process and effectively improving the preheating efficiency and melting effect. Through the mutual cooperation of these technical features, the technical problem of efficiently preheating and melting scrap steel in the quantum arc furnace is solved.

[0033] The setting of the alternating electromagnetic coil can be achieved by arranging multiple coils in the furnace cavity and adjusting the frequency and intensity of the electromagnetic field as needed. The separation design of the preheating area and the melting area can be achieved by setting heat insulation materials or heat insulation barriers inside the furnace body, thereby effectively controlling the temperature gradient.

[0034] The quantum arc furnace of this application makes the preheating and melting process of scrap steel more efficient, uniform and stable through the design of the alternating electromagnetic coil and the separation of the preheating area and the melting area. Compared with the prior art, the technical solution of this application has significant advantages in improving the preheating efficiency and melting effect.

[0035] Furthermore, this application also proposes that on-line monitoring includes real-time monitoring of the contents of carbon, nitrogen, chromium, and molybdenum elements in molten steel using laser-induced breakdown spectroscopy, and real-time monitoring of the surface quality of hot-rolled plates and cold-rolled plates using machine vision.

[0036] Through laser-induced breakdown spectroscopy (LIBS), the contents of carbon, nitrogen, chromium, and molybdenum elements in molten steel can be monitored in real time to ensure that the element contents are within the controlled range, thereby guaranteeing the quality of steel. Machine vision technology is used to monitor the surface quality of hot-rolled and cold-rolled sheets in real time, detect and handle surface defects in a timely manner, and improve the surface quality of products. The combination of the two realizes the comprehensive monitoring of the steel composition and surface quality, ensuring that the products meet the high-quality requirements.

[0037] Laser-induced breakdown spectroscopy generates plasma on the surface of molten steel through high-energy laser pulses and analyzes the spectrum emitted by the plasma to determine the element content. This technology has the advantages of being fast, accurate, and non-contact, and is suitable for high-temperature and high-speed production environments. Machine vision technology captures and analyzes the surface images of hot-rolled and cold-rolled sheets in real time through cameras and image processing algorithms, identifies surface defects such as cracks, pits, and scratches, and feeds the detection results back to the control system for timely adjustment of production parameters.

[0038] Therefore, the online monitoring system using laser-induced breakdown spectroscopy and machine vision technology can monitor the element content in molten steel and the surface quality of steel plates in real time and accurately. Compared with the existing technology, it significantly improves the quality control level of steel production, reduces the errors and delays of manual inspection, and improves production efficiency and product quality.

[0039] Furthermore, this application also proposes that non-destructive testing includes using ultrasonic flaw detectors to detect cracks, pores, and inclusion defects inside steel billets and steel plates.

[0040] Non-destructive testing includes using ultrasonic flaw detectors to detect cracks, pores, and inclusion defects inside steel billets and steel plates. The ultrasonic flaw detector can penetrate the interior of the steel by emitting and receiving ultrasonic signals to detect various internal defects. Ultrasonic waves will reflect and refract when encountering the interfaces of different materials. By analyzing the characteristics of the echo signals, the location and nature of the defects can be determined. By using ultrasonic flaw detectors, defects such as cracks, pores, and inclusions inside steel billets and steel plates can be effectively detected. This method has the advantages of high precision, non-destructiveness, and fast detection speed, and can timely discover and eliminate quality problems in the production process without affecting the material properties, thereby improving product quality and production efficiency.

[0041] The core technical feature of an ultrasonic flaw detector lies in its ability to transmit and receive ultrasonic signals. Specifically, an ultrasonic flaw detector emits high-frequency ultrasonic signals through one or more transducers. These signals can penetrate steel and reflect and refract when encountering interfaces of different materials. The echo signals are received and analyzed by electronic devices to identify the location and nature of internal defects. As a preferred implementation, phased array ultrasonic flaw detection technology can be adopted. This technology can achieve rapid scanning and imaging of a large area without moving the probe through multiple transducer arrays. In addition, to improve the detection accuracy, other non-destructive testing technologies, such as eddy current testing and magnetic particle testing, can be combined to comprehensively analyze the detection results.

[0042] By using an ultrasonic flaw detector for non-destructive testing in this application, it is possible to quickly and accurately detect defects such as cracks, pores, and inclusions inside billets and steel plates without damaging the steel. Compared with the prior art, this application has the advantages of high detection accuracy, fast detection speed, and non-destructiveness, and can effectively improve the quality and production efficiency of products. Therefore, this application has significant technological progress and practical application value in steel quality control.

[0043] Furthermore, this application also proposes that in step (i), it also includes cleaning, filtering, and denoising the collected data to eliminate outliers and interference signals.

[0044] The data processing technical features in step (i) include cleaning, filtering, and denoising. These technical features play an important role in solving the problems of outliers and interference signals in the data. Through cleaning, obvious errors and unreasonable values in the data can be removed; through filtering, the data can be smoothed to reduce random noise; through denoising, interference signals in the data can be further eliminated. These technical features cooperate with each other to ensure the accuracy and reliability of the data. Through these data processing steps, the data quality can be effectively improved, enabling subsequent machine learning algorithms to perform deep learning based on more accurate data, discover potential laws and problems, and thus achieve automated and intelligent control of the production process.

[0045] The cleaning step can screen abnormal data by setting reasonable thresholds and rules. For example, data points that significantly exceed the normal range can be excluded. The filtering step can use a low-pass filter to remove high-frequency noise or use a Kalman filter to smooth the data. The denoising process can use methods such as wavelet transform to eliminate noise signals in the data. These processing methods can be used alone or in combination to achieve the best data cleaning effect.

[0046] This application significantly improves data accuracy and reliability by adding cleaning, filtering, and denoising techniques to the data collection process. Compared to existing technologies, this application can more effectively eliminate outliers and interference signals in the data, allowing subsequent machine learning and data analysis to be based on more accurate data, thereby improving the automation and intelligent control level of the production process.

[0047] Furthermore, the present application also proposes that in step (j), the machine learning algorithm includes predicting the production status in the future period based on the process model and the current status, and adjusting parameters in advance to achieve preventive control.

[0048] Machine learning algorithms are used to predict future production conditions by building process models and current conditions. These predictions are used to proactively adjust production parameters, enabling preventive control. This allows adjustments to occur before problems occur, ensuring a more stable and efficient production process and reducing potential production failures and quality issues.

[0049] The core of machine learning algorithms lies in predicting future production conditions and adjusting parameters in advance. Specifically, this can be achieved through the following methods: 1. Build a predictive model for the production process based on historical data and current conditions, using methods such as regression analysis or time series analysis. 2. Employ deep learning techniques to train neural network models on production data to extract underlying patterns and features. 3. Utilize ensemble learning methods to combine multiple models to improve prediction accuracy and robustness. 4. Based on the prediction of future production conditions, combine optimization algorithms to identify the optimal production parameter adjustment plan.

[0050] Through the above-mentioned technical means, preventive control of the production process can be achieved, production failures and quality issues can be reduced, and production efficiency and stability can be improved. Compared with the existing technology, the technical solution of this application can detect potential problems earlier and make timely adjustments, avoiding the limitations of passively responding to problems in traditional methods. As a result, this application has significant advantages in improving the level of automation and intelligence in the production process.

[0051] Furthermore, the present application also proposes that the ratio of Ar / N mixed gas in the AOD refining stage is 80:20, and a two-stage spray gun structure is adopted, with the argon spray gun and the nitrogen spray gun working alternately.

[0052] Technical features of the AOD refining stage include an 80:20 Ar / N2 mixed gas ratio and a two-stage spray gun structure, with argon and nitrogen spray guns operating alternately. These features, through the optimal gas ratio and spray gun structure design, provide more effective gas agitation and mixing during the smelting process, thereby improving carbon and nitrogen removal efficiency and optimizing smelting results.

[0053] Specifically, in the AOD refining stage, the ratio of Ar / N mixed gas is 80:20, which can ensure the uniform distribution of argon and nitrogen during the smelting process and enhance the stirring effect of the gas. The two-stage lance structure design enables the argon lance and the nitrogen lance to work alternately, realizing the dynamic adjustment and optimization of the gas. The use of the argon lance helps with decarburization, while the nitrogen lance helps with denitrification, thereby effectively controlling the carbon and nitrogen content in the molten steel. As a preferred embodiment, the two-stage lance structure may include adjustable nozzles to adapt to different smelting requirements. In addition, the smelting effect can be further optimized by controlling the working frequency and flow rate of the lance.

[0054] By adopting the above technical solutions, the present application realizes the optimization of the gas ratio and the lance structure in the AOD refining stage, significantly improving the removal efficiency of carbon and nitrogen during the smelting process. Compared with the prior art, the present application provides a more effective gas stirring and mixing effect by reasonably designing the gas ratio and the lance structure, thereby optimizing the smelting effect. This not only improves the production efficiency but also ensures the quality stability and consistency of the ultra-pure ferritic stainless steel.

[0055] Furthermore, the present application also proposes that in the continuous casting process, segmented cooling is adopted in the secondary cooling zone, with a specific water ratio of 0.2 - 0.4 L / kg, a casting speed of 0.6 - 1.4 m / min, a mold electromagnetic stirring current of 200 - 400 A, and a frequency of 1 - 4 Hz.

[0056] Segmented cooling ensures the uniform cooling of the molten steel during continuous casting by controlling the cooling intensity in different regions, reducing internal stress and defects. The parameter settings of the specific water ratio of 0.2 - 0.4 L / kg and the casting speed of 0.6 - 1.4 m / min make the cooling process more precise and controllable. The mold electromagnetic stirring further optimizes the crystallization process of the molten steel through the settings of the current of 200 - 400 A and the frequency of 1 - 4 Hz, ensuring the quality and uniformity of the billet. These technical features cooperate with each other to solve the control problems of the cooling and crystallization processes of the molten steel in the continuous casting process, improving the quality and production efficiency of the continuous casting billet, while reducing production defects and energy consumption.

[0057] Segmented cooling can be achieved by setting multiple cooling segments in the secondary cooling zone, with each cooling segment independently controlling the flow rate and temperature of the cooling water. The control of the specific water ratio can be achieved by adjusting the output of the water pump and the spraying method of the cooling water. The control of the casting speed can be achieved by adjusting the drawing speed of the continuous casting machine. The current and frequency of the mold electromagnetic stirring can be set and adjusted through the control system of the electromagnetic stirring device. Further, advanced sensors and control systems can be used to monitor and adjust various parameters in real time to ensure the stability and consistency of the cooling and crystallization processes.

[0058] By adopting technical means such as segmented cooling, precisely controlling the specific water volume and casting speed, and optimizing the parameters of mold electromagnetic stirring, this application effectively solves the control problems in the molten steel cooling and crystallization processes during the continuous casting process. Compared with traditional cooling and crystallization methods, these technical means can significantly improve the quality and production efficiency of continuous casting billets, reduce internal stress and defects, lower energy consumption, and achieve an efficient and stable continuous casting production process.

[0059] Furthermore, this application also proposes that after pickling, electrolytic polishing treatment is carried out, with a current density of 5 - 20 A / dm 2 , the pH value of the electrolyte is 2 - 3, the polishing time is 5 - 15 minutes, and the surface roughness Ra ≤ 0.05 μm.

[0060] Through electrolytic polishing treatment, the surface quality after pickling can be further improved, ensuring that the surface roughness meets the high standard of Ra ≤ 0.05 μm. This treatment step removes surface micro-defects by controlling the current density, pH value of the electrolyte, and polishing time, and finally obtains a smooth and uniform surface.

[0061] The current density of the electrolytic polishing treatment can be selected within the range of 5 - 20 A / dm 2 , and the specific value can be adjusted according to actual needs. The pH value of the electrolyte is controlled between 2 - 3, and this range helps to improve the polishing efficiency and reduce the generation of by-products. The polishing time is controlled within 5 - 15 minutes, which can ensure the surface quality while avoiding material loss caused by over-polishing. Specifically, the selection of the current density can be optimized according to the initial roughness and polishing requirements of the material, the pH value of the electrolyte can be controlled by adjusting the acid concentration, and the polishing time can be appropriately adjusted according to the actual effect.

[0062] This application significantly improves the surface finish after pickling to reach the high standard of Ra ≤ 0.05 μm through electrolytic polishing treatment technology. Compared with traditional mechanical polishing methods, electrolytic polishing treatment not only has higher efficiency but also can more evenly remove surface micro-defects, avoiding new scratches and defects that may be introduced by mechanical polishing. Thus, the surface quality of the product has been significantly improved, meeting higher usage requirements.

[0063] Furthermore, this application also proposes that in the VOD vacuum refining stage, a calcium treatment process is added. The calcium content of the Al-Ca alloy in the calcium treatment is 6 - 10 wt%, the addition amount is 0.08 - 0.15% of the mass of the molten steel, and it is added in two portions.

[0064] By adding a calcium treatment process during the VOD vacuum refining stage, the calcium in the Al-Ca alloy is used to improve the purity and properties of the molten steel. The calcium treatment is carried out by adding the Al-Ca alloy in two portions, ensuring that the calcium content is 6-10 wt%, and the addition amount accounts for 0.08-0.15% of the mass of the molten steel. The calcium treatment can effectively remove inclusions in the molten steel and improve the fluidity of the molten steel, thereby improving the quality of the final product. This technical solution solves the problem of how to further improve the quality of ultra-pure ferritic stainless steel during the VOD vacuum refining stage by optimizing the calcium treatment process. By controlling the calcium content and addition amount, while ensuring the purity of the molten steel, the properties of the molten steel can be improved, and ultimately high-quality ultra-pure ferritic stainless steel can be produced.

[0065] Specifically, the implementation methods of the calcium treatment process can include the following: First, the Al-Ca alloy can be evenly added to the molten steel in two portions through a mechanical dosing device to ensure the uniform distribution of calcium. Second, the time interval of addition can be controlled during the calcium treatment so that calcium can fully react with the inclusions in the molten steel to form compounds that are easy to remove. Third, the effect of the calcium treatment can be further enhanced by optimizing the temperature and vacuum degree of the calcium treatment. In addition, other refining processes, such as electromagnetic stirring, can be combined to enhance the distribution and reaction efficiency of calcium in the molten steel.

[0066] Thus, through the above calcium treatment process, the purity and fluidity of the molten steel can be significantly improved, inclusions can be reduced, the properties of the molten steel can be enhanced, and ultimately high-quality ultra-pure ferritic stainless steel can be produced. Compared with the prior art, the application of the calcium treatment process in this application during the VOD vacuum refining stage further improves the purity and properties of the molten steel and optimizes the production process, having significant technical advantages.

[0067] It should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An integrated smelting and rolling process for ultra-pure ferritic stainless steel, characterized in that, It includes the following steps: (a) Scrap steel is preheated to 600 - 700°C in a quantum arc furnace by an alternating electromagnetic field and then melted by power supply, controlling the melting temperature and time; (b) In the AOD refining stage, Ar / N mixed gas is introduced, the stirring intensity is ≥1000 L / min, and the carbon content is controlled ≤0.005%; (c) In the VOD vacuum refining stage, the vacuum degree is maintained ≤30 Pa, and decarburization is carried out until C + N ≤0.01%; (d) In the continuous casting process, an electromagnetic stirring crystallizer is adopted, the superheat of molten steel is ≤20°C, the thickness of the continuous casting slab is 200 - 250 mm, and the proportion of equiaxed crystals is ≥50%; (e) In the hot rolling process, the thickness of the intermediate billet in rough rolling is 30 - 50 mm, the finishing rolling exit temperature is 780 - 820°C, and the coiling temperature is 550 - 650°C; (f) In the cold rolling process, a three - stage gradient roll is adopted, and the rolling force is reduced by 8 - 12% for each pass; (g) The double - stage annealing process includes recrystallization annealing and secondary annealing. Among them, the temperature of recrystallization annealing is 850 - 950°C, the annealing time is 5 - 8 min, the temperature of secondary annealing is 700 - 750°C, and the annealing time is 10 - 15 min; (h) Pickling is carried out using a mixed solution of nitric acid and hydrofluoric acid with a volume ratio of 4:1 - 2:1, and the pickling time is 10 - 30 minutes; (i) Collect, store and analyze various production data of on - line monitoring and non - destructive testing; (j) Adopt machine learning algorithms to perform in - depth learning on production data to discover potential laws and problems; (k) Feed the data back to the control system, adjust production parameters in real time, and realize the automatic and intelligent control of the production process.

2. The integrated smelting and rolling process of the ultra-pure ferritic stainless steel according to claim 1, wherein, The quantum arc furnace includes: (i) An alternating electromagnetic coil is arranged in the furnace cavity, with a frequency of 10 - 100 kHz and a magnetic field intensity ≥5 T; (ii) The scrap steel preheating area is separated from the melting area, and the temperature gradient in the preheating area is ≤50°C / m.

3. The integrated smelting and rolling process of the ultra-pure ferritic stainless steel according to claim 1, characterized in that, On - line monitoring includes using laser - induced breakdown spectroscopy to monitor the content of carbon, nitrogen, chromium, and molybdenum elements in molten steel in real time, and using machine vision to monitor the surface quality of hot - rolled plates and cold - rolled plates in real time.

4. The integrated smelting and rolling process of the ultra-pure ferritic stainless steel according to claim 1, characterized in that, Non - destructive testing includes using an ultrasonic flaw detector to detect cracks, pores, and inclusion defects inside steel billets and steel plates.

5. The integrated smelting and rolling process of the ultra-pure ferritic stainless steel according to claim 1, characterized in that, In step (i), it also includes cleaning, filtering, and denoising the collected data to eliminate outliers and interference signals.

6. The integrated smelting and rolling process of the ultra-pure ferritic stainless steel according to claim 1, characterized in that, In step (j), the machine learning algorithm includes predicting the production state in a future period based on the process model and the current state, and adjusting parameters in advance to achieve preventive control.

7. The integrated smelting and rolling process of the super pure ferritic stainless steel according to claim 1, characterized in that, In the AOD refining stage, the proportion of Ar / N mixed gas is 80:20, a two - stage spray gun structure is adopted, and the argon spray gun and the nitrogen spray gun work alternately.

8. The integrated smelting and rolling process of the ultra-pure ferritic stainless steel according to claim 1, characterized in that, In the continuous casting process, the secondary cooling zone adopts segmented cooling, the specific water volume is 0.2 - 0.4 L / kg, the drawing speed is 0.6 - 1.4 m / min, the electromagnetic stirring current of the crystallizer is 200 - 400 A, and the frequency is 1 - 4 Hz.

9. The integrated smelting and rolling process for super pure ferritic stainless steel according to claim 1, characterized in that, After pickling, electrolytic polishing treatment is carried out with a current density of 5 - 20 A / dm 2 , the pH value of the electrolyte is 2 - 3, the polishing time is 5 - 15 minutes, and the surface roughness Ra ≤ 0.05 μm.

10. The integrated smelting and rolling process of the ultra-pure ferritic stainless steel according to claim 1, wherein, In the VOD vacuum refining stage, a calcium treatment process is added. In the calcium treatment, the calcium content of the Al - Ca alloy is 6 - 10 wt%, the addition amount is 0.08 - 0.15% of the mass of molten steel, and it is added in two times.

Images