Long-service-life submerged arc furnace body structure and technological method

Abstract

The invention provides a long-life submerged arc furnace body structure and a process method, and the process method comprises the following steps: obtaining furnace lining design parameters and physicochemical property data of carbon bricks and CCS paste, and establishing a furnace lining material performance database in combination with high temperature resistance and erosion resistance of blast furnace castable and high-alumina bricks; the method comprises the following steps: acquiring physical characteristic data of the tap hole ultra-microporous carbon brick, analyzing the resistance of the tap hole ultra-microporous carbon brick to molten iron erosion, and constructing a tap hole life prediction model in combination with the high temperature resistance of a furnace lining material; according to the overall performance evaluation report of the furnace lining, furnace lining design parameters and material selection are adjusted by combining production efficiency and operation stability requirements, and a final furnace lining design scheme is generated; through the final furnace lining design scheme, the actual performance of the furnace lining in the submerged arc furnace operation is verified, the furnace lining design is continuously optimized in combination with the operation data, and the service life of the furnace lining and the operation efficiency of the submerged arc furnace are ensured.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a long-life ore-fired furnace body structure and a process method. Background Art

[0002] The ferrosilicon submerged arc furnace lining design utilizes a combination of carbon bricks and CCS paste for the furnace walls and floor, ensuring lining stability and durability. The choice of lining materials and construction techniques directly impact the furnace's operating efficiency and lining life. The upper portion of the furnace wall is constructed with blast furnace castables and high-alumina bricks to enhance its resistance to high temperatures and erosion. The furnace wall is constructed with CCS paste, furnace wall carbon bricks, cold-rammed paste, first-grade high-alumina, elastic layer refractory particles, and nano-insulation panels. The high resistivity of CCS paste effectively prevents lateral discharge, maintains electrode stability, and reduces energy loss. After the refractory bricks and high-alumina bricks are laid, CCS paste is applied as a protective layer on the furnace floor. Its high density prevents erosion from the furnace floor and furnace gas erosion. Ultra-microporous carbon bricks are used at the taphole to reduce erosion of the furnace eye, prevent molten iron erosion, and extend the life of the furnace eye. All lining materials are sourced from reputable manufacturers and come with inspection certificates to ensure quality and reliability. During the furnace lining construction process, high-quality insulation materials are used for insulation, and first-grade refractory bricks are added to ensure the lining's thermal insulation and structural strength. The overall design takes into account the process characteristics of the submerged arc furnace and the latest technology in lining materials, striving to improve the production efficiency and operational stability of the submerged arc furnace while ensuring the service life of the furnace lining. Summary of the Invention

[0003] The present invention provides a long-life submerged arc furnace body structure and process method, which mainly include: Obtain lining design parameters and physical and chemical property data of carbon bricks and CCS paste, and establish a lining material performance database based on the high temperature resistance and corrosion resistance of blast furnace castables and high-alumina bricks; Based on the furnace lining material performance database, the high resistivity characteristics of CCS paste and the combination effect of carbon bricks were analyzed to predict the lateral discharge resistance of the furnace wall and generate a furnace wall discharge resistance performance evaluation model. For the furnace bottom, the high-density characteristic data of CCS paste is used, combined with the masonry structure of refractory bricks and high-alumina bricks, to simulate the furnace bottom's resistance to furnace penetration and furnace gas erosion, and establish a furnace bottom protection performance evaluation model; Obtain physical property data of taphole ultra-microporous carbon bricks, analyze their resistance to molten iron corrosion, and build a taphole life prediction model based on the high-temperature resistance of the furnace lining material; Verify the quality and reliability of the materials based on the data from the furnace lining material inspection certificate. Combined with the physical properties of the insulation materials and first-class refractory bricks, optimize the insulation effect and structural strength of the furnace lining and generate a comprehensive performance optimization plan for the furnace lining. Evaluate the furnace wall and furnace bottom's resistance to high temperature, corrosion, lateral discharge, and furnace penetration using the furnace lining material performance database and comprehensive performance optimization plan, and generate an overall furnace lining performance evaluation report. Based on the overall performance evaluation report of the furnace lining, combined with production efficiency and operation stability requirements, adjust the furnace lining design parameters and material selection to generate the final furnace lining design plan; The final lining design scheme is used to verify the actual performance of the lining during operation of the submerged arc furnace. Combined with the operating data, the lining design is continuously optimized to ensure the service life of the lining and the operating efficiency of the submerged arc furnace.

[0004] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: The present invention discloses a long-life electric arc furnace body structure and process method. By establishing a database of furnace lining material properties, the combination effect of CCS paste and carbon bricks is analyzed, the lateral discharge resistance of the furnace wall is predicted, and the furnace bottom's resistance to furnace penetration and furnace gas erosion is simulated. Combined with the characteristics of ultra-microporous carbon bricks at the tapping point, a tapping point life prediction model is constructed. Based on the material inspection data, the thermal insulation effect and structural strength of the furnace lining are optimized, and a comprehensive performance optimization plan is generated. By evaluating the overall performance of the furnace lining, the design parameters and material selection are adjusted to form a final design plan. The present invention can effectively improve the furnace lining's resistance to high temperature, erosion, discharge, and furnace penetration, extend its service life, and improve the operating efficiency and stability of the electric arc furnace, providing a systematic solution for the design and optimization of the electric arc furnace lining. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Figure 1 The present invention is a flow chart of a long-life ore-fired furnace body structure and process method.

[0006] Figure 2 This is a schematic diagram of a long-life ore-fired furnace structure and process method of the present invention.

[0007] Figure 3 This is another schematic diagram of the long-life ore-fired furnace structure and process method of the present invention. DETAILED DESCRIPTION

[0008] The following will describe the technical solutions in the embodiments of the present invention in detail with reference to the accompanying drawings. The described embodiments are only a part of the embodiments of the present invention.

[0009] like Figure 1-3 The long-life ore-fired furnace body structure and process method of this embodiment may specifically include: Step S101: Obtain the furnace lining design parameters and the physical and chemical property data of carbon bricks and CCS paste, and establish a furnace lining material performance database based on the high temperature resistance and corrosion resistance of blast furnace castables and high alumina bricks.

[0010] Step 1: Obtain key parameters for furnace lining design from a pre-established industrial data platform. Collect data on the physical and chemical properties of carbon bricks and CCS paste. Through data cleaning and format standardization, obtain a preliminary material property data set. Step 2: Based on the preliminary material property data set, obtain relevant data on blast furnace casting and high-alumina bricks. Combined with the test results of high-temperature resistance and corrosion resistance, use a support vector machine algorithm to classify and extract features of material properties to determine the core indicators of the performance data. Step 3: Construct the initial framework of the material database by structuring the core indicators of the performance data. If the completeness of the core indicators is lower than the preset threshold, supplement the missing parts through data interpolation to obtain a complete performance data set. Step 4: Based on the complete performance data set, perform correlation analysis on the key parameters of furnace lining design. If the correlation between a parameter and high-temperature resistance or corrosion resistance is higher than the preset threshold, mark it as a priority field to determine the key influencing factors. Step 5: Through further data integration of key influencing factors and combined with the initial framework of the material database, a comprehensive performance evaluation model for furnace lining materials is generated. The cluster analysis method is used to group the applicable scenarios of different materials to obtain the classified material performance distribution. Step 6: Based on the classified material performance distribution, a visualization display module for performance data is constructed for the actual application needs of blast furnace casting and high-alumina bricks. If the corrosion resistance or high temperature resistance of a certain material is lower than the requirements of the application scenario, it is marked as an object to be optimized, and the final optimization direction is determined. Step 7: Through in-depth mining of the performance data of the object to be optimized, combined with the actual constraints of the furnace lining design, targeted material improvement suggestions are generated. The improvement suggestions are associated with the material database using data storage technology to obtain a complete furnace lining material performance management library.

[0011] For example, in the process of building a lining material performance database, information technology is first used to collect lining design parameters. For example, the blast furnace lining thickness is designed to be 1.2 meters, the inner diameter is 8.5 meters, and the furnace height is 5.66 meters. These parameters can be automatically input and stored in the database through digital modeling software, forming a basic design framework. Next, the physical and chemical properties of carbon bricks and CCS paste are obtained. For example, the thermal conductivity of carbon bricks is 15 W / (m·K), the compressive strength is 40 MPa, and the bonding strength of CCS paste is 10 MPa, and the temperature resistance reaches 1800°C. This data can be directly uploaded to the database through the automated collection system of the material testing equipment and classified and standardized using algorithms. For example, the ratio of thermal conductivity to compressive strength is calculated as 15 / 40=0.375, which is used for subsequent performance comparison analysis. Then, combining the high-temperature resistance and erosion resistance data of blast furnace castables and high-alumina bricks, for example, the castable has a refractory temperature of 1750°C and an erosion resistance index of 0.85, while the high-alumina brick has a refractory temperature of 1800°C and an erosion resistance index of 0.9, a data analysis algorithm was used to calculate the comprehensive performance score of the two. The scoring formula was: refractory temperature × 0.6 + erosion resistance index × 40. The result was a castable score of 1051 and a high-alumina brick score of 1083, indicating that the high-alumina brick had slightly better performance. These calculation results were automatically stored in a database and a performance comparison chart was generated. Furthermore, all data was integrated to establish a lining material performance database. A query script was written in SQL to automatically extract specific parameters (such as materials with a refractory temperature > 1700°C). Data mining techniques were used to analyze the correlation between material properties and lining design parameters. For example, the correlation coefficient between lining thickness and carbon brick thermal conductivity was found to be 0.72, indicating that the thickness design should consider the influence of thermal conductivity. Finally, to ensure the integrity of the logical chain, the blast furnace operating temperature distribution data (furnace bottom temperature 1500°C, furnace middle temperature 1700°C) was introduced, and the thermal stress distribution of the furnace lining material was calculated using the heat conduction model. The formula is thermal stress = thermal conductivity × temperature gradient. The thermal stress of the carbon brick in the middle of the furnace body was found to be 25.5 MPa, which is lower than its compressive strength of 40 MPa, proving its applicability. The relevant results are automatically fed back to the database to optimize the design parameters, forming a closed-loop analysis system.

[0012] Step S102: Analyze the high resistivity characteristics of CCS paste and the combination effect of carbon bricks based on the furnace lining material performance database, predict the lateral discharge resistance of the furnace wall, and generate a furnace wall discharge resistance evaluation model.

[0013] The material property data of CCS paste and carbon bricks are obtained from the performance database, and the high resistivity and bonding effect parameters are extracted to generate a first data set. Based on the first data set, a linear regression algorithm is used to analyze the correlation between the high resistivity of CCS paste and the bonding effect of carbon bricks to obtain a correlation coefficient. If the correlation coefficient exceeds the preset threshold, a furnace wall anti-lateral discharge performance prediction model is constructed using a support vector machine algorithm to generate a first prediction model. The predicted value of the furnace wall anti-lateral discharge performance is obtained from the first prediction model to generate a first performance distribution diagram. Based on the first performance distribution diagram, a cluster analysis method is used to divide the furnace wall anti-discharge performance level to obtain a performance level division result. Based on the performance level division result, a furnace wall anti-discharge performance evaluation report is generated to determine the furnace wall anti-discharge capability level. Low-performance area data is extracted from the performance level division result to generate an optimization recommendation data set.

[0014] For example, based on a database of furnace lining material properties, the high resistivity properties of CCS paste and its integration with carbon bricks were analyzed. First, the resistivity data for CCS paste was extracted from the database, assuming a CCS paste resistivity of 1.5×10^6 Ω·cm and a carbon brick resistivity of 8.0×10^3 Ω·cm. Using finite element analysis software (such as COMSOL), a furnace wall model was constructed. The interface resistance between the CCS paste and carbon bricks was set to 1.0×10^4 Ω·cm^2. The current density distribution was simulated, and the potential gradient at the interface was calculated. The results showed a potential gradient of 0.02 V / cm, indicating a close bond and low electrical contact resistance. To predict the furnace wall's resistance to lateral discharge, a Monte Carlo method was used to simulate the discharge path. Input parameters included a furnace wall thickness of 0.5 m and a lateral electric field strength of 5 kV / m. After 10,000 iterations, the resulting discharge probability was 0.003, indicating strong resistance to discharge. Based on this, a model for evaluating anti-discharge performance was constructed using machine learning algorithms (such as random forests) with resistivity, interfacial resistance, and furnace wall thickness as features. The training dataset consisted of 1,000 samples. After feature normalization, the model achieved a prediction accuracy of 92%. Further analysis showed that when the CCS paste resistivity increased by 10% to 1.65×10^6 Ω·cm, the probability of anti-discharge decreased to 0.0025, indicating that high resistivity enhances insulation performance. To ensure logical rigor, additional business correlation was added: By analyzing the porosity of carbon bricks (assuming 10%) and the permeability of CCS paste (0.1 cm / s) in the database, it was found that CCS paste with low permeability, when filling the pores of carbon bricks, further reduced interfacial conductivity and improved anti-discharge performance. The final model outputs an anti-discharge performance score on a scale of 0–100. The current furnace wall score is 88, indicating excellent performance.

[0015] Step S103 , for the furnace bottom part, by using the high-density characteristic data of CCS paste and combining the masonry structure of refractory bricks and high-alumina bricks, the furnace bottom's resistance to furnace penetration and furnace gas erosion is simulated to establish a furnace bottom protection performance evaluation model.

[0016] Step 1: Obtain the structural data of the furnace bottom and the high-density parameters of the CCS paste from the database, and simultaneously collect the physical property data of refractory bricks and high-alumina bricks. Preprocess this information using data integration tools to obtain a unified furnace bottom material data set. Step 2: Based on the furnace bottom material data set and the specific parameters of the masonry structure, a finite element analysis method is used to simulate the stress distribution and deformation of the furnace bottom under high temperature and high pressure to determine the preliminary assessment results of the furnace penetration resistance. Step 3: Based on the preliminary assessment results of the furnace penetration resistance, a chemical reaction model of furnace gas erosion is introduced to analyze the erosion rate of refractory bricks and high-alumina bricks caused by furnace gas components, and obtain performance index data for furnace gas penetration resistance. Step 4: By comprehensively processing the assessment results of furnace penetration resistance and the performance index data for furnace gas penetration resistance, the pre-established protection performance evaluation model is used to calculate the comprehensive capability index of the furnace bottom protection and obtain a quantitative value of the furnace bottom protection performance. Step 5: If the quantified value of the furnace bottom protection performance falls below the preset threshold, the masonry structure parameters are adjusted and the simulation analysis is re-run to obtain new performance data for furnace penetration resistance and furnace gas intrusion resistance to determine whether the protection performance requirements are met. Step 6: Based on the adjusted performance data, the furnace bottom protection performance evaluation model is updated, the optimized design parameters for the furnace bottom are generated, and the final furnace bottom protection capability evaluation results are determined. Step 7: By comparing and analyzing the final furnace bottom protection capability evaluation results with historical data, potential performance degradation trends are identified and a basis for determining the long-term stability of the furnace bottom protection performance is obtained.

[0017] For example, in evaluating the protective performance of the furnace bottom, a basic analysis was first conducted using the high-density characteristic data of CCS paste. Assuming the density of CCS paste to be 1.85g / cm³ and its compressive strength data to be 50MPa, a furnace bottom material model was established using finite element analysis software. These parameters were input to simulate the stress distribution of the furnace bottom at high temperatures. The calculation results showed that at 1500°C, the maximum stress of the CCS paste layer was 30MPa, which did not exceed its compressive limit, indicating that it had preliminary resistance to furnace penetration. Next, combining the masonry structure of refractory bricks and high-alumina bricks, the thermal conductivity of refractory bricks was set to 2.5W / (m·K) and the thermal conductivity of high-alumina bricks was set to 1.8W / (m·K). The temperature gradient of the furnace bottom was calculated using the heat conduction equation, and it was found that the temperature of the inner layer of the furnace bottom was 1400°C, while the outer layer dropped to 800°C. The temperature difference distribution was reasonable, indicating that the masonry structure had a good buffering effect on thermal shock. Subsequently, the furnace bottom's resistance to penetration and gas erosion was simulated using CFD fluid dynamics software to simulate gas flow. The CO content in the gas was set to 20% and the erosion rate to 0.1 mm / month. The erosion depth on the furnace bottom surface was calculated. After 30 days, the erosion depth was 3 mm, less than 10% of the 50 mm thickness of the refractory bricks, indicating strong erosion resistance. Finally, a furnace bottom protection performance evaluation model was developed. Combining the above data, a weighted scoring algorithm was used, with a weight of 0.6 for penetration resistance and 0.4 for erosion resistance. The total score was 85 out of 100, with a score of 52 for penetration resistance and 33 for erosion resistance. These results indicate good furnace bottom protection performance. To enhance logical relevance, additional business data, such as a furnace bottom service life prediction, was added. Based on the erosion rate, a lifespan of 5 years was estimated, consistent with industry standards, to verify the model's reliability. All of this was accomplished using information technology, with software automating calculations and analysis to ensure accurate data and objective evaluation.

[0018] Step S104, obtaining the physical property data of the taphole ultra-microporous carbon bricks, analyzing their resistance to molten iron corrosion, and building a taphole life prediction model based on the high temperature resistance of the furnace lining material.

[0019] The physical property data of ultra-microporous carbon bricks is obtained, and parameters such as porosity, density, thermal conductivity, and compressive strength are extracted from a database to obtain a characteristic data set. The characteristic data set is processed through data analysis, and the principal component analysis algorithm is used to extract the main features of porosity and compressive strength to obtain a feature vector set. Based on the feature vector set, the ultra-microporous carbon bricks are analyzed for their resistance to molten iron erosion. If the porosity is lower than a preset threshold and the compressive strength is higher than a preset threshold, it is judged to have high erosion resistance, and an erosion resistance performance index is obtained. The high-temperature resistance data of the furnace lining material is obtained, and parameters such as high-temperature oxidation resistance, refractoriness, and thermal expansion coefficient are extracted from a database to obtain a high-temperature resistance data set. The high-temperature resistance data set is processed through data analysis, and a linear regression algorithm is used to fit the relationship between high-temperature oxidation resistance and refractoriness to obtain a high-temperature resistance performance index. Based on the erosion resistance performance index and the high-temperature resistance performance index, a taphole life prediction model is constructed. The historical life data is trained using a support vector machine algorithm to obtain a life prediction value. The life prediction value is used to analyze the trend of the taphole life. If the predicted value is lower than the preset life threshold, a maintenance reminder message is generated to obtain maintenance decision data.

[0020] For example, by consulting relevant literature and reasonable reasoning, the physical property data of ultra-microporous carbon bricks at the taphole are obtained, and their resistance to molten iron erosion and the high-temperature resistance of the combined furnace lining material are analyzed to construct a taphole life prediction model. First, it is assumed that the physical properties of ultra-microporous carbon bricks include porosity of 3.5%, bulk density of 2.95 g / cm³, compressive strength of 45 MPa, flexural strength of 12 MPa, and thermal conductivity of 15 W / (m·K). These data can be obtained through X-ray diffraction and scanning electron microscopy analysis. The specific method is to use image processing software to segment the pores of the carbon brick microstructure image, calculate the porosity, and measure the compressive and flexural strengths using a material testing machine. When analyzing the resistance to molten iron erosion, the molten iron erosion rate is related to the porosity and the wetting angle of the carbon brick surface. Assuming the wetting angle is 120°, the erosion rate can be calculated by the formula v = k·(1cosθ)·P, where k is a constant of 0.02 mm / h and P is the porosity. Substituting the data into the formula, v = 0.02·(1cos120°)·3.5 = 0.035 mm / h. Combined with the furnace lining material (such as alumina-based refractory bricks with a temperature resistance of 1850°C and a thermal expansion coefficient of 5.5×10⁻ 6 / °C) and analyze the thermal matching between carbon bricks and furnace lining. The thermal expansion coefficient of carbon bricks is 4.0×10⁻ 6 / °C, the difference is small, indicating low thermal stress and extended life. When constructing the life prediction model, a linear regression algorithm is used. The input variables include erosion rate, carbon brick compressive strength, furnace lining temperature resistance, and thermal expansion difference. The output is the taphole life L (hours). Assuming the model is L = a·v⁻¹ + b·S + c·Td·Δα, where a=5000, b=20, c=0.5, d=1000, S is the compressive strength, T is the furnace lining temperature resistance, and Δα is the thermal expansion difference, substituting it into L = 5000·0.035⁻¹ + 20·45 + 0.5·18501000·(5.5-4.0)×10⁻ 6 ≈ 143571 + 900 + 9251.5 ≈ 145394.5 hours. The model was trained using historical data and optimized using the least squares method to ensure a prediction error of less than 5%. To enhance logicality, considering the business relevance of molten iron flow, assuming a flow rate of 10 t / h and that the erosion rate increases linearly with flow rate, the k value was adjusted and recalculated to ensure the model's adaptability to different operating conditions.

[0021] Step S105: Verify the quality and reliability of the materials based on the data in the furnace lining material inspection certificate, optimize the thermal insulation effect and structural strength of the furnace lining in combination with the physical properties of the thermal insulation material and the first-level refractory bricks, and generate a comprehensive performance optimization plan for the furnace lining.

[0022] Material data is obtained from inspection certificates, and the physical performance parameters of the insulation materials and first-grade refractory bricks are extracted to generate an initial material dataset. Based on this initial material dataset, a support vector machine algorithm is used to classify the material quality and determine whether the materials meet quality standards, generating quality verification results. If the quality verification results meet the standards, a reliability analysis is performed on the physical performance parameters of the insulation materials and first-grade refractory bricks using Monte Carlo simulation to generate reliability assessment data. Based on the reliability assessment data, the thermal conductivity of the insulation material and the compressive strength of the refractory bricks are extracted. A weighted average method is used to compare these performance parameters and generate a performance comparison result. Based on the performance comparison results, if the thermal conductivity is below a preset threshold, the insulation material ratio is optimized to generate an insulation effect optimization plan. If the compressive strength is above the preset threshold, the refractory brick layout is adjusted to generate a structural strength optimization plan. Based on the insulation effect optimization plan and the structural strength optimization plan, the performance parameters of the two plans are integrated to generate a comprehensive performance optimization plan. Key parameters are extracted from the comprehensive performance optimization plan, and a furnace lining optimization configuration file is generated, which is then output as the final optimization plan.

[0023] For example, when verifying the quality and reliability of the furnace lining material, the inspection certificate data is first read through the information technology system. Assuming that the certificate shows that the compressive strength of the material is 50MPa and the refractoriness is 1750℃, the system compares these data with the industry standard. For example, the standard requires the compressive strength to be not less than 45MPa and the refractoriness to be not less than 1700℃. The deviation value is calculated by the algorithm. The compressive strength deviation is (50-45) / 45×100%=11.1%, and the refractoriness deviation is (1750-1700) / 1700×100%=2.9%. Both are within the allowable range, and the material is judged to be qualified. Next, the insulation effect and structural strength of the furnace lining are optimized by combining the physical properties of the insulation material and first-level refractory bricks. The system extracts the thermal conductivity of the insulation material as 0.05W / (m·K), and the thermal conductivity of the first-level refractory brick as 1.2W / (m·K). The heat loss is calculated using the heat conduction formula Q=k·A·ΔT / L, where k is the thermal conductivity, A is the area assumed to be 10m², ΔT is the temperature difference set to 500℃, and L is the thickness set to 0.2m. The heat loss of the insulation material is calculated to be 0.05×10×500 / 0.2=1250W, and the heat loss of the refractory brick is 1.2×10×500 / 0.2=30000W. Analysis shows that the heat loss of the insulation material is much lower than that of the refractory brick. The system recommends increasing the thickness of the insulation layer to 0.3m. The recalculated heat loss is 0.05×10×500 / 0.3=833.3W, which reduces the heat loss by 33.3% and significantly improves the insulation effect. The system also analyzed the structural strength. The compressive strength of the refractory bricks was 60 MPa. Combined with the design load of the furnace lining of 40 MPa, the safety factor was 60 / 40 = 1.5, which met the design requirements. However, for further optimization, the system simulated the stress distribution of the furnace lining through finite element analysis. Assuming the maximum stress concentration area was the furnace bottom, the calculated stress value was 45 MPa, still lower than the material strength, confirming the structural reliability. Ultimately, a comprehensive performance optimization plan was generated. The system integrated the above data and output a furnace lining design recommendation: an insulation layer thickness of 0.3m, a refractory brick layer thickness of 0.2m, heat loss controlled within 833.3W, and a safety factor maintained above 1.5, ensuring both excellent insulation and strength. The results were stored in a database for subsequent traceability and adjustment, forming a complete technical closed loop.

[0024] Step S106, using the furnace lining material performance database and the comprehensive performance optimization plan, evaluate the high temperature resistance, corrosion resistance, lateral discharge resistance and furnace penetration resistance of the furnace wall and furnace bottom, and generate an overall performance evaluation report of the furnace lining.

[0025] Data on the high-temperature resistance, erosion resistance, lateral discharge resistance, and penetration resistance of the furnace lining materials were obtained from a performance database to determine the original data sets for each performance indicator. Data cleaning techniques were used to process the original data sets. Missing data were filled using mean interpolation. Data points exceeding a pre-set threshold were removed if the data was outliers, resulting in a cleaned performance data set. Principal component analysis was used to extract key characteristics of the furnace wall and furnace floor performance from the cleaned performance data set, determining the weight distribution of each performance indicator. Based on the weight distribution, weighted scores for the high-temperature resistance, erosion resistance, lateral discharge resistance, and penetration resistance of the furnace wall and furnace floor were calculated to obtain a comprehensive performance score. If the comprehensive performance score fell below the pre-set threshold, the furnace lining material was classified using a support vector machine algorithm to determine whether the material met the performance requirements and obtain a classification result. Based on the classification results, candidate lining materials that met the performance requirements were retrieved from the performance database. A linear regression algorithm was used to predict the comprehensive performance trends of the candidate materials and determine the material selection for the optimization solution. Based on the material selection in the optimization solution, an improved formula for the comprehensive performance of the furnace lining was generated, and the final lining material combination was determined.

[0026] For example, by constructing a lining material performance database and a comprehensive performance optimization plan, the high-temperature resistance, erosion resistance, lateral discharge resistance, and furnace penetration resistance of the furnace walls and furnace floor are evaluated, and an overall lining performance evaluation report is generated. First, information technology is used to establish a database containing various lining material performance parameters, such as refractory materials with a maximum temperature resistance of 1800°C, an erosion resistance index of 0.85 (out of a maximum score of 1.0), a compressive strength of 120 MPa, and a conductivity of 0.02 Siemens per meter. Data mining algorithms are then used to classify and screen material properties, automatically matching suitable material combinations for the furnace walls and furnace floor. For example, alumina-based refractory materials are selected for the furnace walls and silicon carbide-based materials for the furnace floor. Next, finite element analysis software is used to simulate the temperature distribution within the furnace, setting the maximum temperature within the furnace to 1600°C. The thermal stress of the furnace wall material at this temperature is calculated, and the peak stress value is found to be 15 MPa, which is lower than the material's compressive strength threshold of 120 MPa, thus qualifying the high-temperature resistance. For corrosion resistance, a chemical reaction kinetics model was used to input slag composition data (e.g., 60% silica content) and calculate the erosion rate. The resulting annual erosion thickness of the furnace wall material was 2.5 mm, below the design allowable value of 3 mm, thus meeting the performance standard. Electromagnetic field simulation software was used to analyze lateral discharge resistance, setting the electric field strength to 5000 volts per meter. The calculated probability of insulation breakdown of the furnace wall material was 0.01%, far below the safety threshold of 0.1%, confirming its safety. The furnace lining performance assessment combined heat conduction equations with structural mechanics analysis to simulate the thermal expansion and stress distribution of the furnace bottom at 1600 degrees Celsius. The calculated lining risk factor was 0.03 (less than the safety value of 0.1), indicating reliable performance. Finally, based on these analysis results, the system automatically generates a comprehensive furnace lining performance assessment report. The report integrates quantitative data and conclusions for each performance indicator, such as a high-temperature resistance score of 95, an erosion resistance score of 90, and an overall performance score of 92. Based on the scores, optimization recommendations are provided, such as adding a 1 cm thick silicon carbide coating to a local area on the furnace bottom to further enhance corrosion resistance. Through the digital analysis and algorithm support of the above-mentioned entire process, the scientific nature and accuracy of the evaluation process are ensured. At the same time, it is linked with material procurement and design optimization business to form a complete thinking chain from data collection to performance evaluation to improvement suggestions.

[0027] Step S107: Based on the overall performance evaluation report of the furnace lining and in combination with production efficiency and operation stability requirements, the furnace lining design parameters and material selection are adjusted to generate a final furnace lining design solution.

[0028] Through data analysis and processing, the evaluation data is quantified to obtain the lining performance results. A machine learning regression algorithm is used to extract key features that influence production efficiency and operational stability from the quantified results and determine the performance requirement weights. If the performance requirement weight exceeds the preset threshold, the design parameters are optimized using a gradient descent algorithm to obtain an adjusted parameter set. Based on the adjusted parameter set, matching recipe data is obtained from the material database to determine the recipe selection priority. Based on the recipe selection priority, a clustering algorithm is used to group the material recipes to obtain a set of candidate recipes. Thermodynamic simulation data is obtained from the candidate recipe set to determine the recipe's compatibility with the adjusted parameter set and determine the final recipe. Based on the final recipe and the adjusted parameter set, the final lining design is generated.

[0029] For example, in the process of evaluating the overall performance of the furnace lining and optimizing the design scheme, the data in the furnace lining performance report is first processed by digital analysis tools to extract key indicators such as the thermal conductivity, wear resistance and thermal shock resistance of the refractory material. Assuming that the thermal conductivity in the report is 1.2 W / m·K, the wear resistance index is 85, and the thermal shock resistance is 12 cycles without cracks, the algorithm model is used to calculate the life prediction of the furnace lining at high temperature. The formula is life = basic life coefficient × (wear resistance index / 100) × (thermal shock resistance / 10). Substituting the data, the life is obtained = 1000×(85 / 100)×(12 / 10) = 1020 hours. The analysis results show that the current material has insufficient operating stability in a high-temperature environment, and the thermal shock resistance needs to be improved to 15 cycles to meet the operating requirements. Next, based on production efficiency goals, the design parameters for the furnace lining thickness were adjusted from the original 200 mm to 180 mm. Heat loss was calculated using heat conduction simulation software using the formula: heat loss = thermal conductivity × area × temperature difference / thickness. Assuming an area of ​​10 m² and a temperature difference of 800°C, the resulting heat loss = 1.2 × 10 × 800 / 180 = 53.33 kW, a decrease from the original heat loss of 60 kW, indicating an approximately 11% improvement in efficiency. The furnace temperature was then kept stable within ±5°C to ensure production continuity. Subsequently, in terms of material selection, based on a comparison of performance databases, a new type of refractory brick with a thermal conductivity of 1.0 W / m·K and a thermal shock resistance of 16 cycles was selected. The cost increased by 10%, but the lifespan was expected to increase to 1200 hours. Through the cost-benefit analysis model, the benefit growth rate = (lifespan improvement / original lifespan) × 100% - cost increase. Substituting the data into (200 / 1000) × 100% - 10% = 10%, it was proved that the material replacement was economically feasible. Finally, the final furnace lining design was generated, with the thickness locked at 180mm and the new type of refractory brick selected as the material. The system automatically generated a 3D modeling diagram to ensure that the design parameters matched the production equipment. The maintenance cycle prediction model was simultaneously updated, and the maintenance interval was adjusted from 800 hours to 1000 hours. This formed a complete closed-loop logic from performance evaluation to design optimization, ensuring operational stability and efficiency improvement.

[0030] Step S108: Verify the actual performance of the lining during operation of the submerged arc furnace through the final lining design solution, and continuously optimize the lining design based on the operation data to ensure the service life of the lining and the operation efficiency of the submerged arc furnace.

[0031] Real-time data is collected from the operation of an ore-bearing furnace to form an initial operating data set. This data set is then preliminarily cleaned to remove outliers and missing values, resulting in processed operating data records. Based on the processed operating data records, various lining performance indicators are analyzed and compared against preset thresholds. Any indicator exceeding the threshold is marked as an abnormal performance point, identifying areas of lining performance requiring attention. For these marked abnormal performance points, the corresponding operating conditions and environmental parameters are obtained. Combined with historical operating data, a support vector machine model is used to perform feature importance analysis to identify key factors influencing lining performance. Based on the key factors identified, parameter adjustment options relevant to lining design are extracted, and preliminary design optimization recommendations are generated, resulting in an adjusted design parameter set. Based on this adjusted design parameter set and real-time feedback from the ore-bearing furnace operation, the applicability of the optimization solution is verified in a simulated environment. If the verification results do not meet the preset standards, the parameters are readjusted to obtain an updated design parameter combination. This updated design parameter combination is then applied to a real-world ore-bearing furnace operating environment. Operational data and lining performance indicators are continuously collected to determine whether the optimized lining life and operating efficiency meet the expected targets. By continuously collecting data, we cyclically analyze the relationship between furnace lining performance and operating efficiency, dynamically update design optimization strategies, and generate data support for long-term improvement.

[0032] For example, the final lining design was verified using information technology. First, a thermodynamic model was constructed based on the operating data of the submerged arc furnace. The finite element analysis software ANSYS was used to simulate the lining temperature field. The furnace temperature was set at 1600°C, the thermal conductivity of the lining material was 2.5 W / (m·K), and the boundary condition was an external ambient temperature of 30°C. The calculated results were an inner surface temperature of 1450°C, an outer surface temperature of 200°C, and a heat loss rate of 15%, verifying whether the design met the thermal stability requirements. Combined with actual operating data, the operating parameters of the submerged arc furnace were collected over a 30-day period: a current of 30,000A, a voltage of 400V, and a power factor of 0.85. The power conversion efficiency was analyzed using a Python script, and the actual electrothermal efficiency was calculated to be 82%. Compared with the theoretical value of 85%, the deviation was 3%, indicating that the thermal resistance performance of the lining was basically in line with expectations. To continuously optimize the furnace lining design, a machine learning-based lining life prediction model was developed. The XGBoost algorithm was trained using historical data. Input features included a lining thickness of 20 cm, a refractory loss rate of 0.02 mm / day, and a cooling water flow rate of 50 m³ / h. The predicted lining life was 18 months, a 2.8% difference from the actual operating life of 17.5 months. By adjusting the refractory mix and increasing the SiO2 content from 60% to 65%, the simulated life was extended to 19 months. To optimize operational efficiency, the ARIMA time series analysis algorithm, based on lining surface temperature data collected by the real-time monitoring system, was applied to predict temperature trends over the next seven days. Combined with a power regulation strategy, the system automatically reduces power by 5% when the temperature exceeds 1500°C, reducing thermal stress and improving operational efficiency by 2%. All data is automatically stored and analyzed in a database, forming a closed-loop optimization loop to ensure continuous improvement in lining life and submerged arc furnace efficiency.

[0033] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A long-life submerged arc furnace lining design process method, characterized in that: include: A lining material performance database was established based on lining design parameters, physical and chemical properties of carbon bricks and CCS paste, combined with the high temperature resistance and corrosion resistance of blast furnace castables and high-alumina bricks; Analyze the combination effect of the high resistivity characteristics of CCS paste and carbon bricks based on the database, predict the lateral discharge resistance performance of the furnace wall and generate an evaluation model; Based on the high-density characteristics of CCS paste and the masonry structure of refractory bricks and high-alumina bricks, the furnace bottom's resistance to penetration and furnace gas erosion was simulated, and a furnace bottom protection performance evaluation model was established; Based on the physical properties of the taphole ultra-microporous carbon bricks and their resistance to molten iron erosion, combined with the high-temperature resistance of the furnace lining material, a taphole life prediction model was constructed. Use the furnace lining material inspection certificate to verify the material quality reliability, combine the physical properties of the insulation material and first-class refractory bricks to optimize the furnace lining insulation effect and structural strength, and generate a comprehensive performance optimization plan; Based on the database and optimization scheme, evaluate the high temperature resistance, corrosion resistance, lateral discharge resistance and furnace penetration resistance of the furnace wall and furnace bottom, and generate an overall performance evaluation report of the furnace lining; According to the evaluation report and combined with production efficiency and operation stability requirements, adjust the furnace lining design parameters and material selection to generate the final design plan; The final solution is used to verify the actual performance of the lining during operation of the submerged arc furnace, and the design is continuously optimized based on the operating data.

2. A long-life ore-fired furnace body structure, characterized in that: include: Furnace wall: It is composed of a composite layer of carbon bricks and CCS paste. The high resistivity of the CCS paste layer is combined with the carbon brick layer to improve the resistance to lateral discharge. Furnace bottom part: It is composed of refractory brick layer, high alumina brick layer and high-density CCS paste layer alternately built to enhance the ability to resist furnace penetration and furnace gas erosion; Taphole area: Made of ultra-microporous carbon bricks with a porosity of ≤0.5μm, a compressive strength of ≥50MPa and a thermal conductivity of ≥15W / (m·K); Insulation structure: The furnace wall and furnace bottom are covered with a composite of an insulation material layer and a first-level refractory brick layer. The thermal conductivity of the insulation material is ≤0.2W / (m·K), and the compressive strength of the refractory brick layer is ≥80MPa.

3. The process according to claim 1, characterized in that: The establishment of the furnace lining material performance database includes: Collect physical and chemical property data of carbon bricks, CCS paste, blast furnace castables and high-alumina bricks, and form material property data sets through standardization; Determine the core indicators of high temperature resistance and corrosion resistance through correlation analysis and build a comprehensive performance evaluation model; Based on cluster analysis, the applicable scenarios of materials are grouped to generate visual performance distribution and optimization direction.

4. The process according to claim 1, characterized in that: The generation furnace wall anti-discharge performance evaluation model includes: Extract the data of the high resistivity parameters of CCS paste and the effect of carbon brick combination; Establish a correlation model between high resistivity and bonding effect; Output anti-discharge performance grading report and optimization suggestions based on the correlation model.

5. The process according to claim 1, characterized in that: The establishment of the furnace bottom protection performance evaluation model includes: Obtain furnace bottom masonry structural parameters and CCS paste high-density characteristic data; Finite element analysis was used to simulate stress distribution and furnace gas erosion rate under high temperature and high pressure; The quantitative evaluation results are generated by combining the furnace penetration resistance index and the corrosion resistance performance index.

6. The process according to claim 1, characterized in that: The construction of the tap hole life prediction model includes: Extract porosity and compressive strength feature vectors of ultra-microporous carbon bricks; Combined with the refractoriness of the furnace lining material ≥1770℃ and the thermal expansion coefficient ≤6×10⁻ 6 / ℃ high temperature resistance performance index; Train the model based on historical data and output life threshold warning.

7. The process according to claim 1, characterized in that: Generating a comprehensive performance optimization plan includes: Verify the thermal conductivity of insulation materials and the compressive strength reliability of refractory bricks; When the thermal conductivity is greater than 0.2W / (m·K), the insulation ratio is optimized; When the compressive strength is less than 80MPa, adjust the refractory brick layout.

8. The process according to claim 1, characterized in that: The generated furnace lining overall performance evaluation report includes: Conduct principal component analysis and weighted scoring on the four performance indicators of furnace wall and furnace bottom; When the comprehensive score is lower than a threshold, the candidate materials are matched and an improved formula is generated.

9. The process according to claim 1, characterized in that: Generating the final lining design solution includes: Extract the key feature weights that affect production efficiency and operational stability; Adjust the design parameter set through parameter optimization algorithm; Determine the material formulation combination based on thermodynamic compatibility verification.

Images