Method and device for sintering ore blending based on uniformly mixed ore liquid phase generation amount

Abstract

The invention discloses a method and a device for sintering ore blending based on uniformly mixed ore liquid phase generation amount. According to the method, a prediction model is established on the basis of a multi-group ore preparation scheme and corresponding strength data, the implicit correlation between the mixed ore liquid phase generation amount and the sintered ore strength is converted into quantifiable mathematical mapping, and the prediction model is called by determining the target strength to be achieved in current production to reversely derive the liquid phase generation amount constraint condition. And generating an optimized sintering ore blending scheme by taking the uniformly mixed ore liquid phase generation amount as a core constraint condition. According to the method, a closed-loop regulation and control mechanism of data modeling-constraint generation-scheme optimization is formed, the rapid iteration constraint condition and the ore blending scheme can be adjusted according to different sintered ore strength requirements, the production adaptability is improved, meanwhile, the sintering consolidation key parameter, namely the liquid phase generation amount, serves as a link, and the sintering consolidation efficiency is improved. Theoretical and technical support is provided for fine control of the sintering process, and the overall target of improving the strength stability of the sintered ore is finally achieved.

Description

Technical Field

[0001] The present application relates to the field of metallurgy technology, and in particular to a method and device for sintering and blending ore based on the amount of liquid phase generated by mixing ore. Background Art

[0002] In steel production, sintered ore is a key raw material for blast furnace smelting, and its quality significantly impacts steel production. During the sintering process, carbon combustion provides heat, and iron oxides undergo redox reactions. The formation of a liquid phase (such as calcium ferrite and silicates) is central to sinter consolidation, and the amount of effective liquid phase is directly related to sinter quality. Iron ore particle size composition is a key indicator of the effective liquid phase. Particles 1-3 mm in diameter act as nucleation particles, reacting minimally with mineral fluxes and producing virtually no liquid phase. The liquid phase primarily forms from adherent particles smaller than 0-1 mm reacting with calcium flux. The amount of liquid phase in the raw material can be calculated based on the mass content of particles of this size. After mixing and granulation, the mixture develops a specific particle size composition (0-3 mm <15%, 3-5 mm 40%-50%, 5-10 mm ≤30%, >10 mm ≤10%), creating an effective binding phase and meeting the required sinter consolidation strength.

[0003] my country currently needs to rationalize ore blending to reduce costs and produce sintered ore that meets blast furnace requirements. Current sinter blending relies heavily on manual raw material matching, a cumbersome and complex process that fails to meet the requirements of automated and intelligent control. Automated sinter blending constraint generation methods exist that use the chemical composition of sintered ore as a blending constraint. However, in practice, using sintered ore chemical composition as a blending constraint makes it difficult to guarantee drum strength, effectively ensuring that the sintered ore drum meets blast furnace smelting requirements.

[0004] Therefore, how to achieve more intelligent sintering ore blending while ensuring that the sintering ore drum strength meets the requirements of blast furnace smelting is an urgent problem that technical personnel in this field need to solve. Summary of the Invention

[0005] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a method and device for sintering ore blending based on the amount of mixed ore liquid phase generated, which can achieve more intelligent sintering ore blending while ensuring that the sintered ore drum strength meets the blast furnace smelting requirements.

[0006] In a first aspect, an embodiment of the present application provides a method for sintering ore blending based on the amount of liquid phase generated by mixing ore, comprising: Based on the finished sinter strength data corresponding to various sintering ore blending schemes, a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sinter is established; Determine the intensity index to be achieved as the target intensity; The prediction model is called to calculate the range of the amount of the mixed ore liquid phase generated required to achieve the target strength, and to generate constraint conditions for the amount of the mixed ore liquid phase generated; An optimized sintering ore blending plan is generated based on the constraints.

[0007] In one embodiment, the method of establishing a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sintered ore based on the finished sintered ore strength data corresponding to the multiple sintering ore blending schemes includes: Obtain chemical composition, burnout rate and particle size distribution data of various raw materials as metallurgical performance parameters; Collect the finished sintered ore strength data corresponding to various raw material and fuel ratios during the sintering production process; Calculating the amount of liquid phase generated by the mixed ore based on the raw material and fuel ratio and corresponding metallurgical performance parameters; Arranging the generated amount of the mixed ore liquid phase and the corresponding finished sintered ore strength data to generate an original data set; A prediction model is established based on the original data set.

[0008] In one embodiment, the calculation of the liquid phase generated by the mixed ore based on the raw material fuel ratio and the corresponding metallurgical performance parameters includes: The amount of liquid phase generated by the mixed ore is calculated based on the content of adhered particles, the burnout rate and the amount of dry material in the raw material and fuel ratio.

[0009] In one embodiment, the calculation of the amount of liquid phase generated by the mixed ore based on the content of adhered particles, the burnout rate, and the amount of dry material in the raw material and fuel ratio includes: The amount of liquid phase generated by the mixed ore is calculated according to formula 1; The formula 1:

[0010] in, is the amount of mixed ore liquid phase generated, is the dry material amount of each raw material, The content of 0 to 1 mm particles in the raw material, is the burnout rate of each raw fuel in the raw fuel ratio.

[0011] In one embodiment, establishing a prediction model based on the original data set includes: The relationship between liquid phase generation and strength was fitted based on nonlinear regression model; Training and validating the nonlinear regression model according to the original data set; The nonlinear regression model that meets the accuracy requirements after verification is used as the prediction model.

[0012] In one embodiment, before training and validating the nonlinear regression model based on the original data set, the method further includes: Performing data cleaning on the original data set; Perform data standardization on the cleaned dataset.

[0013] In one embodiment, the calling of the prediction model to calculate the range of the mixed ore liquid phase generation amount required to achieve the target strength and generating the constraint conditions for the mixed ore liquid phase generation amount include: Calculating the upper limit and lower limit of the amount of mixed ore liquid phase generated required to achieve the target strength according to the prediction model; According to the upper limit value and the lower limit value, generate Formula 2 as a constraint condition; The formula 2:

[0014] Wherein, A is the lower limit value, B is the upper limit value, is the ratio of each raw material, is the liquid phase composition of each raw material.

[0015] In one embodiment, after generating the optimized sintering ore blending plan based on the constraint conditions, the method further includes: Conducting a cost analysis on the optimized sintering ore blending scheme and generating a cost analysis report; Predicting the performance of the finished sintered ore based on the optimized sintering ore blending scheme and generating a performance evaluation report; Output the optimized sintering ore blending plan and the corresponding cost analysis report and performance evaluation report.

[0016] In a second aspect, an embodiment of the present application provides a device for sintering and blending ore based on the amount of liquid phase generated by mixing ore, comprising: The model building module is used to establish a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sintered ore based on the finished sintered ore strength data corresponding to various sintering ore blending schemes; An indicator determination module is used to determine the intensity indicator to be achieved as the target intensity; A constraint calculation module is used to call the prediction model to calculate the range of mixed ore liquid phase generation required to achieve the target strength and generate constraint conditions for the mixed ore liquid phase generation; A scheme generation module is used to generate an optimized sintering ore matching scheme based on the constraint conditions.

[0017] In a third aspect, an embodiment of the present application provides a server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for sintering and blending ore based on the amount of liquid phase generated by the mixed ore are implemented as described above.

[0018] The method for sintering ore matching based on the amount of liquid phase generated in mixed ore provided in this application establishes a prediction model based on multiple groups of ore matching schemes and corresponding strength data, converts the implicit correlation between the amount of liquid phase generated in mixed ore and the strength of sintered ore into a quantifiable mathematical mapping, and calls the prediction model to reversely deduce the liquid phase generation constraint by determining the target intensity to be achieved in the current production, and generates an optimized sintering ore matching scheme with the amount of liquid phase generated in mixed ore as the core constraint. This method forms a closed-loop control mechanism of data modeling-constraint generation-scheme optimization, which can adjust the fast iterative constraints and ore matching schemes according to different sintered ore strength requirements, improve production adaptability, and at the same time, use the liquid phase generation, a key parameter of sintering consolidation, as a link to provide theoretical and technical support for the refined control of the sintering process, and ultimately achieve the overall goal of improving the strength stability of sintered ore.

[0019] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A schematic flow chart of a method for sintering and blending ore based on the amount of liquid phase generated by mixed ore provided in an embodiment of the present application is shown; Figure 2 An exemplary structural block diagram of a device for sintering and blending ore based on the amount of liquid phase generated by mixed ore provided in an embodiment of the present application is shown; Figure 3 A schematic diagram of the structure of a computer system suitable for implementing a server according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0021] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the invention are shown in the accompanying drawings.

[0022] It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. Although the embodiments of the present application provide the method operation instruction steps shown in the following embodiments or drawings, more or fewer operation instruction steps may be included in the method based on routine or no creative labor. In steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiments of the present application. During the actual processing process or when the device is executed, the method may be executed in the order of the methods shown in the embodiments or drawings or in parallel.

[0023] Example 1: This example proposes a method for sintering ore blending based on the amount of liquid phase generated by mixing ore. Please refer to Figure 1 , Figure 1 The flow chart of the method for sintering and blending ore based on the amount of liquid phase generated by the mixed ore provided in this embodiment is shown. Figure 1 As shown, the method includes: S101. Establish a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sintered ore based on the finished sintered ore strength data corresponding to various sintering ore blending schemes; During the sintering process, raw materials partially melt or soften at high temperatures to form a liquid phase, which is the key driving force for the consolidation of sintered ore particles. The amount of liquid phase generated directly affects the mineralogical composition and structural strength of the sintered ore. Insufficient liquid phase leads to insufficient particle consolidation and low strength; excessive liquid phase easily causes over-melting and adhesion, affecting permeability. Therefore, calculating the amount of liquid phase generated is a core intermediate variable for evaluating sintered ore quality.

[0024] This method proposes that during the sinter production process, multiple groups of sintering schemes with different raw material ratios and process conditions are first collected, and the amount of mixed ore liquid phase generated and the strength indicators of the finished sintered ore (such as drum strength) corresponding to each group of schemes are simultaneously measured to form an original data set.

[0025] The original data set was then analyzed and fitted using methods such as nonlinear regression and machine learning. A mathematical model was constructed to quantitatively describe the dynamic relationship between the amount of liquid phase generated in the blended ore and the sinter strength, serving as a prediction model. This prediction model can be used to predict sinter strength based on liquid phase generation, or to infer the required liquid phase generation range based on the target strength, providing data support and decision-making basis for the optimized design of sintering ore blending.

[0026] S102. Determine the intensity index to be achieved as the target intensity; During the sintering ore blending optimization process, specific strength performance indicators (e.g., drum strength TI6.3 ≥ 75%) and compressive strength (e.g., compressive strength) that the finished sintered ore must meet are clearly defined based on blast furnace smelting process specifications, product quality standards, or customer customization requirements. These indicators serve as the core strength targets for ore blending design. This embodiment does not limit the specific strength quantification type of the strength indicators; only drum strength and compressive strength are used as examples. Other strength types can be referenced in the description of this embodiment and are not further elaborated here.

[0027] By quantifying the target strength, a benchmark is provided for the subsequent use of the prediction model to reversely estimate the required liquid phase generation range, making the optimization of the ore blending plan clearly performance-oriented.

[0028] Among them, the specific numerical setting of the target strength is not limited in this embodiment. It is necessary to comprehensively consider the minimum requirements of the smelting process for the sintered ore strength, industry quality standards, raw material costs and other constraints to ensure that the target value meets both production needs and is economically feasible, thereby laying the foundation for the constraint generation and optimization design of the subsequent ore blending plan.

[0029] S103, calling the prediction model to calculate the range of the amount of the mixed ore liquid phase generated required to achieve the target strength, and generating the constraint conditions for the amount of the mixed ore liquid phase generated; Using a predetermined target strength for the finished sintered ore as an input parameter, the established prediction model is used to reverse-engineer the reasonable range of liquid phase production required to achieve this target strength. This range is then used as the liquid phase production range. The model then uses historical data to fit a nonlinear relationship between liquid phase volume and strength. Based on this liquid phase production range, a quantitative constraint, expressed as a mathematical inequality, is generated, explicitly requiring that the total liquid phase production, calculated based on the proportions of each raw material in the blending plan, must fall within this range.

[0030] Through inverse calculations within the prediction model, the sinter strength performance target is converted into a specific limit on the amount of liquid phase generated in the blended ore. This provides core process parameter constraints for the subsequent optimization design of the ore blending scheme, ensuring that sinter strength targets and multi-objective production optimization are achieved while meeting liquid phase requirements. This process embodies the reverse deduction logic from terminal performance indicators to key intermediate variables and provides an engineering implementation path for quantitative control and precise ore blending in sintering production.

[0031] S104. Generate an optimized sintering ore blending plan based on the constraint conditions.

[0032] On the basis of the determined constraint range of the mixed ore liquid phase generation amount, the optimal raw material combination scheme is generated as the sintering ore matching scheme with the raw material ratio as the decision variable.

[0033] The sintering ore blending plan takes the constraint condition of the amount of mixed ore liquid phase generated as the core constraint condition, and can also include multiple constraints such as raw material supply feasibility (such as the available amount range of each raw material), process production requirements (such as alkalinity, magnesium oxide content and other indicator restrictions), cost control goals, etc. It should be noted that in this embodiment, in addition to the constraint condition of the amount of mixed ore liquid phase generated as the core constraint condition, other constraints are not limited. Only the above conditions are introduced as an example. The specific constraints can be set according to the usage requirements in the actual application scenario, and will not be repeated here.

[0034] Based on the above introduction, the method for sintering ore matching based on the amount of liquid phase generated in mixed ore provided in this embodiment establishes a prediction model based on multiple groups of ore matching schemes and corresponding strength data, converts the implicit correlation between the amount of liquid phase generated in mixed ore and the strength of sintered ore into a quantifiable mathematical mapping, and calls the prediction model to reversely deduce the liquid phase generation constraint by determining the target intensity to be achieved in the current production, and generates an optimized sintering ore matching scheme with the amount of liquid phase generated in mixed ore as the core constraint. This method forms a closed-loop control mechanism of data modeling-constraint generation-scheme optimization, which can quickly iterate the constraints and ore matching schemes according to raw material fluctuations or process adjustments, improve production adaptability, and at the same time, use the liquid phase generation, a key parameter of sintering consolidation, as a link to provide theoretical and technical support for the refined control of the sintering process, and ultimately achieve the overall goal of improving the strength stability of sintered ore.

[0035] Example 2: The above embodiment does not limit the specific construction process of the prediction model. In order to achieve accurate mapping of process parameters based on raw material characteristics, this embodiment proposes a construction process of the prediction model. Step S101 establishes a prediction model of the amount of mixed ore liquid phase generated and the strength of the finished sintered ore based on the finished sintered ore strength data corresponding to multiple sintering ore blending schemes. The process can be performed as follows: Step S11, obtaining chemical composition, burnout rate and particle size distribution data of various raw fuels as metallurgical performance parameters; Sintering raw materials and fuels refer to the ore powder, sintering flux, and fuel used in the sintering process. Their physical and chemical properties directly determine the quality and performance of the sintered ore. In this step, the chemical composition, burnout rate, and particle size distribution of the raw materials, sintering flux, and fuel are collected as metallurgical performance parameters.

[0036] Chemical composition refers to the ratio of elements and compounds in the raw fuel (e.g., the content of Fe, SiO2, CaO, MgO, Al2O3, FeO, etc.), and is the basis for determining the thermodynamic conditions for mineral phase transformation and liquid phase formation during the sintering process. Burn-out rate refers to the proportion of mass lost by the raw fuel during high-temperature sintering due to reactions such as volatilization, decomposition, and oxidation, typically expressed as the percentage difference in mass before and after ignition. Particle size distribution refers to the particle size composition and distribution characteristics of the raw fuel particles, often expressed as the mass percentage of different size ranges (e.g., <3mm, 3-5mm, 5-10mm, etc.), reflecting the uniformity of the material's particle size distribution. By quantifying the metallurgical performance parameters of each raw fuel, it can be used to analyze the liquid phase generation, strength, and other properties of the sintered ore at different ratios, thus preventing the failure of the ore blending plan due to differences in raw material characteristics.

[0037] Step S12: collecting the finished sintered ore strength data corresponding to various raw material and fuel ratios during the sintering production process; The raw material fuel ratio refers to the mass ratio combination of raw materials such as iron ore (such as hematite, magnetite), flux (such as limestone, dolomite), and fuel (such as coke powder, anthracite) used in sintering production, such as iron ore powder A accounts for 40%, iron ore powder B accounts for 30%, limestone accounts for 15%, and coke powder accounts for 5%.

[0038] The strength data of finished sintered ore refers to a quantitative indicator that characterizes the sintered ore's ability to resist crushing. It is usually quantified using indicators such as drum strength (TI, such as TI6.3 indicates the proportion of particles with a particle size greater than 6.3 mm), compressive strength or drop strength.

[0039] Each set of raw material and fuel ratios is mapped one-to-one with the sinter strength index of the corresponding production batch to form a data set of ratio combination-strength value. Taking the strength value as drum strength as an example, if ratio scheme X corresponds to a drum strength of 78%, and ratio scheme Y corresponds to a drum strength of 80%, it provides original data support for the subsequent analysis of the impact of ratio changes on strength.

[0040] Step S13: Calculate the amount of liquid phase generated by the mixed ore based on the raw material and fuel ratio and the corresponding metallurgical performance parameters; During the sintering ore blending process, based on the mass proportion of the input raw materials and their metallurgical characteristic parameters, the theoretical generation amount of high-temperature liquid phase during the sintering process can be quantitatively predicted through metallurgical thermodynamic models or empirical formulas.

[0041] The amount of liquid phase generated is the core factor that determines the strength of sintered ore. Accurate calculation can establish a direct correlation between it and the strength. By converting the raw material ratio and reaction characteristics into quantifiable liquid phase generation indicators, and converting the chemical composition and physical properties of the raw materials into process parameters, it provides key theoretical calculation support for the subsequent reverse calculation of the liquid phase amount constraints through the target strength and the generation of optimized ore mixing plans.

[0042] Step S14: collating the generated amount of the mixed ore liquid phase and the corresponding finished sintered ore strength data to generate an original data set; The theoretical calculation parameters (the amount of mixed ore liquid phase generated) under different ore blending schemes are systematically correlated with actual production indicators (the strength of the finished sintered ore) to form a standardized data set.

[0043] By establishing a data pair mapping of ore blending plan-liquid phase volume-intensity, the key parameters in the metallurgical process are converted into calculable and analyzable quantitative data, providing basic support for the establishment of subsequent prediction models.

[0044] Step S15: Establish a prediction model based on the original data set.

[0045] Based on the historical corresponding data of the amount of mixed ore liquid phase generated in sintering production and the strength of the finished sintered ore, the nonlinear correlation between the amount of liquid phase generated and the strength of the sintered ore is explored through machine learning algorithms or statistical analysis methods, and a quantitative mapping relationship between the input liquid phase amount and the output predicted strength is formed. A mathematical model with mapping prediction function is constructed as a prediction model.

[0046] The method for constructing a prediction model provided in this embodiment is based on the metallurgical performance parameters of raw materials and fuels, and converts the thermodynamic conditions and kinetic characteristics of liquid phase generation during the sintering process into quantifiable calculation parameters. By collecting strength data corresponding to multiple groups of ore blending schemes and correlating them with the liquid phase generation amount, in the process of data collation and model establishment, the liquid phase generation amount is used as the key intermediate variable connecting the raw material characteristics and product performance. Through the construction of a structured data set, high-quality training samples are provided for the machine learning algorithm, so that the model can accurately capture the nonlinear influence of liquid phase generation on strength.

[0047] The prediction model ultimately formed by this method inherits the theoretical depth of metallurgical technology and has the prediction accuracy of data science. It provides a reliable quantitative tool for the subsequent reverse analysis of liquid phase constraints based on target strength and the optimization design of ore blending schemes, significantly improving the scientific nature, adaptability and engineering application value of sintered ore strength prediction.

[0048] Example 3: In order to reduce experimental calculations, improve data acquisition efficiency, and reduce experimental costs, this embodiment proposes that step S13 in the above-mentioned embodiment 2 calculates the liquid phase generation amount of the mixed ore based on the raw material fuel ratio and the corresponding metallurgical performance parameters. Specifically, the liquid phase generation amount of the mixed ore can be calculated based on the content of adhered particles in the raw material fuel ratio, the burn rate and the amount of dry material.

[0049] The liquid phase generation amount of the raw materials is directly calculated through the mass content of adhered particles with a particle size of 0 to 1 mm in the raw materials, the burn-off rate and the dry material amount. The reaction activity of fine-grained materials is quantified by the adhered particle content. Compared with the traditional calculation method based only on chemical composition, it more accurately captures the influence of particle size distribution on the liquid phase generation dynamics. The burn-off rate is further combined to correct the mass loss in the high-temperature reaction of the raw materials, so that the calculation of the liquid phase generation amount conforms to the material balance principle. Using the dry material amount as the ratio measurement basis can eliminate the interference of moisture fluctuations on the calculation basis.

[0050] This calculation method does not require additional testing costs, which not only ensures the rigor of the metallurgical mechanism of the calculation model, but also improves the real-time and adaptability of engineering applications, providing a quantitative basis with both theoretical depth and industrial practicality for the optimization of ore blending schemes.

[0051] This embodiment further proposes a calculation formula for calculating the amount of liquid phase generated by the mixed ore based on the content of adhered particles in the raw material and fuel ratio, the burn rate and the amount of dry material, as shown in the following formula 1.

[0052] Formula 1:

[0053] in, is the amount of mixed ore liquid phase generated, is the dry material amount of each raw material, The content of 0 to 1 mm particles in the raw material, It is the burnout rate of each raw fuel in the raw fuel ratio.

[0054] The formula is based on the 0-1mm particle content ( ) as a quantitative indicator of the activity of adhesion particles, accurately anchoring the nucleation-melting core of fine-grained materials during the sintering process. Particles in this size range are easy to form low-melting point eutectics due to their large specific surface area and high interfacial energy. The characterization of a wider particle size range is more mechanism-specific; through The burn-loss rate correction item is used to include the mass loss caused by the high-temperature decomposition of raw materials (such as carbonate CO2 escape and crystal water removal) into the material balance calculation, so that the nominal dry material amount is converted into the effective mass of substances actually participating in the liquid phase reaction, avoiding the overestimation or underestimation of the liquid phase amount due to the burn-loss error; the dry material amount ( ) is used as the measurement benchmark to eliminate the interference of raw material moisture fluctuation on the proportion calculation, and all parameters (particle size screening data, burn-loss rate test value, dry material proportion) are routine detection items in sintering production, without the need for additional sensor investment. The mathematical expression of linear summation conforms to the metallurgical nature of the synergistic effect of multi-component raw materials, and the liquid phase generation amount of each raw material is additive. It is also easy to embed in the industrial control system to realize real-time calculation, providing a direct quantitative tool for optimizing the proportion of fine-grained materials in the ore blending plan and regulating the amount of high-burn-loss raw materials, so that the prediction of liquid phase generation and production practice form a closed-loop feedback.

[0055] Example 4: The above embodiment does not limit the specific model type of the prediction model. In order to fully meet the nonlinear metallurgical mechanism of liquid phase generation and strength formation during sintering, this embodiment proposes that a nonlinear regression model can be used to establish a prediction model.

[0056] Specifically, step S15 of establishing a prediction model based on the original data set can be performed according to the following steps: Step S151, fitting the relationship between the amount of liquid generated and the intensity based on a nonlinear regression model; When the liquid phase is insufficient, strength increases exponentially with liquid phase generation (due to weak inter-particle bonding caused by insufficient binder phase). However, after the liquid phase exceeds a critical value, strength growth slows and may even lead to a loose structure due to overmelting. This nonlinear metallurgical mechanism between liquid phase generation and strength during sintering forms. Nonlinear models can accurately characterize this relationship through polynomials, exponential functions, and other forms, avoiding the mechanistic distortion and prediction errors caused by linear models forced to fit nonlinear data.

[0057] Nonlinear fitting can capture high-order interaction effects in the data, such as the combined effect of the synergistic effect of different raw material liquid phases on the strength. Compared with linear models that only describe a single linear relationship, it can significantly improve the goodness of fit in complex industrial scenarios (such as R 2 The value is increased by 15%-20%), and is particularly suitable for the quantitative characterization of nonlinear coupling effects in multi-group mineralization schemes.

[0058] Step S152: training and verifying the nonlinear regression model based on the original data set; Step S153: The nonlinear regression model that meets the accuracy requirements after verification is used as the prediction model.

[0059] The model training process can optimize nonlinear parameters through mechanisms such as cross-validation, and can adapt to the strength response characteristics under different raw material structures. In this embodiment, there is no limitation on the training and verification process of the model. You can refer to the introduction of relevant implementation methods and will not go into details here.

[0060] Before training and validating the nonlinear regression model based on the original dataset, the original dataset can be further cleaned and then normalized to ensure the reliability and generalization of the prediction model. Data cleaning uses methods such as quantile truncation and interpolation to remove outliers and correct missing values. This prevents abnormal data from interfering with model training, such as preventing a set of erroneous liquid phase data from causing a shift in the strength prediction curve. This ensures that the dataset input to the model conforms to the actual laws of metallurgical production.

[0061] Furthermore, the dimensions and numerical ranges of the features in the raw data vary significantly. Directly inputting these features into the model can cause the gradient descent process to favor features with large values ​​(such as dry matter content) while ignoring smaller but critical features (such as the proportion of fine particles). Normalization (such as Z-score normalization or Min-Max normalization) can map all features to a uniform scale, allowing the model to equally capture the impact of each feature on strength. For example, this can prevent the nonlinear contribution of fine particle content to strength from being masked by a large liquid phase generation value.

[0062] Of course, in addition to data cleaning and standardization, other data preprocessing methods can also be used. This is not limited in this embodiment. Corresponding preprocessing can be performed according to the data needs in the actual application scenario, and will not be repeated here.

[0063] Embodiment 5: In order to convert the range of mixed ore liquid phase generation into a quantifiable control boundary, step S103 calls the prediction model to calculate the range of mixed ore liquid phase generation required to achieve the target strength. The process of generating the constraint conditions for the mixed ore liquid phase generation can be specifically executed using the following formula 2. First, the upper and lower limits of the mixed ore liquid phase generation required to achieve the target strength are calculated according to the prediction model, and then formula 2 is generated as the constraint condition based on the upper and lower limits.

[0064] Formula 2 is specifically:

[0065] Among them, A is the lower limit, B is the upper limit, is the ratio of each raw material, is the liquid phase composition of each raw material.

[0066] The interval is converted into the ratio of each raw material by formula 2 ( ) and liquid phase generation contribution ( ) linear constraints to achieve the reverse deduction of strength index → ​​liquid phase volume control → raw material ratio optimization.

[0067] Formula 2 converts the liquid phase constraint into a linear inequality constraint, which can be embedded in a linear programming (LP) or nonlinear programming (NLP) optimization model to solve the optimal ore allocation solution in conjunction with constraints such as raw material cost and inventory. For example, while satisfying the liquid phase constraint (Formula 2), raw material procurement costs can be simultaneously optimized to achieve a multi-objective optimization of achieving strength requirements and minimizing costs. Of course, this embedding is not necessary, and this is not a limitation in this embodiment.

[0068] Example 6: After generating the optimized sintering ore blending scheme, in order to facilitate user decision-making, the optimized sintering ore blending scheme can be further cost analyzed to generate a cost analysis report; at the same time, the performance of the finished sintered ore can be predicted for the optimized sintering ore blending scheme to generate a performance evaluation report; then the optimized sintering ore blending scheme and the corresponding cost analysis report and performance evaluation report are output simultaneously.

[0069] The core content of a cost analysis report may include, but is not limited to, quantifying raw material costs, breaking down cost structures, comparing costs, and optimizing value. Cost analysis verifies the economic feasibility of a solution, providing production managers with intuitive cost data to assist in determining the economic viability of different mix ratios, thereby balancing performance requirements with cost control.

[0070] The core content of a performance evaluation report may include, but is not limited to, quantitative predictions of sinter performance indicators, prediction methods and models, performance comparisons, and risk assessments. By quantitatively predicting key sinter indicators, performance prediction ensures that the optimization plan meets blast furnace production requirements while also identifying potential quality risks in the ore blending scheme. This can also guide secondary optimization of the ore blending scheme, such as adjusting the raw material mix in the event that the performance prediction falls short of expectations.

[0071] After generating an optimized sintering ore blending plan, this embodiment uses a cost analysis report to quantify the cost structure of the entire chain, such as raw material input and energy consumption loss, and dynamically evaluates the economic feasibility of the plan in combination with real-time price data; pre-verifies the physical properties of the sintered ore (such as drum strength) and metallurgical indicators (such as reducibility) through the performance evaluation report, and simulates the impact of raw material fluctuations on quality based on historical data and mechanism models, so as to avoid risks such as insufficient strength and excessive composition in advance; finally, through the coordinated output of dual reports and optimization plans, the post-test of traditional empirical ore blending is transformed into data-driven pre-control, which not only improves the cost competitiveness and quality reliability of the ore blending plan, but also provides parameter traceability support for the smooth operation of the blast furnace, and promotes the upgrade of sintering production to digital and intelligent decision-making.

[0072] Embodiment seven: Further references Figure 2 , which shows an exemplary structural block diagram of a device for sintering and ore matching based on the amount of mixed ore liquid phase generated according to an embodiment of the present application, which mainly includes: a model building module, an indicator determination module, a constraint calculation module and a scheme generation module. The device for sintering and ore matching based on the amount of mixed ore liquid phase generated adopts a modular design and realizes intelligent sintering and ore matching through four core units.

[0073] The model building module is used to establish a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sintered ore based on the finished sintered ore strength data corresponding to various sintering ore blending schemes; An indicator determination module is used to determine the intensity indicator to be achieved as the target intensity; A constraint calculation module is used to call the prediction model to calculate the range of mixed ore liquid phase generation required to achieve the target strength and generate constraint conditions for the mixed ore liquid phase generation; The scheme generation module is used to generate optimized sintering ore matching schemes based on constraint conditions.

[0074] In the system fusing treatment device provided in this embodiment, the model construction module deeply integrates the metallurgical mechanism with the data-driven algorithm based on the historical data of multiple groups of ore blending schemes, and the established prediction model can accurately capture the nonlinear relationship between liquid phase generation and strength; the indicator determination module converts production demand into a clear target strength value, and through linkage with the downstream blast furnace ironmaking process parameters, the ore blending scheme directly serves the whole process production optimization; the constraint calculation module reversely deduces the upper and lower limits of liquid phase generation through the prediction model, and converts the abstract strength target into a quantifiable process constraint; the solution generation module, under the liquid phase quantity constraint, combines the raw material cost, inventory status and other multi-dimensional constraints, and quickly searches for the optimal ratio combination through linear programming or intelligent algorithm. This device transforms the traditional sintering ore blending from an extensive mode relying on manual experience to a data-driven precise control mode, providing core technical support for steel enterprises to improve quality and reduce costs.

[0075] It should be noted that the system fuse processing device introduced in this embodiment can refer to the system fuse processing method introduced in the above embodiments, and the repeated parts will not be repeated in this embodiment.

[0076] Embodiment 8: Reference below Figure 3 , Figure 3 A schematic diagram of the structure of a computer system suitable for implementing a server according to an embodiment of the present application is shown.

[0077] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for the system's operating instructions. CPU 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0078] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, mouse, and the like; an output section 307 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 308 including devices such as a hard disk; and a communication section 309 including a network interface card such as a LAN card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0079] In particular, according to the embodiment of the present application, the above reference flow chart Figure 1 The described processes can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the method illustrated in the flowchart. In such an embodiment, the computer program contains program code for executing the method illustrated in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When the computer program is executed by the central processing unit (CPU) 301, the aforementioned functions defined in the system of the present application are performed.

[0080] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operating instructions of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the aforementioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operating instruction, or can be implemented using a combination of dedicated hardware and computer instructions.

[0081] The units or modules involved in the embodiments described in this application may be implemented in software or hardware. The units or modules described may also be provided in a processor. The names of these units or modules do not, in certain circumstances, constitute limitations on the units or modules themselves.

[0082] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by a specific combination of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned disclosed concepts. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for sintering ore blending based on the amount of liquid phase generated by mixing ore, characterized in that: include: Based on the finished sinter strength data corresponding to various sintering ore blending schemes, a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sinter is established; Determine the intensity index to be achieved as the target intensity; The prediction model is called to calculate the range of the amount of the mixed ore liquid phase generated required to achieve the target strength, and to generate constraint conditions for the amount of the mixed ore liquid phase generated; An optimized sintering ore blending plan is generated based on the constraints.

2. The method according to claim 1, wherein The method of establishing a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sintered ore based on the finished sintered ore strength data corresponding to the various sintering ore blending schemes includes: Obtain chemical composition, burnout rate and particle size distribution data of various raw materials as metallurgical performance parameters; Collect the finished sintered ore strength data corresponding to various raw material and fuel ratios during the sintering production process; Calculating the amount of liquid phase generated by the mixed ore based on the raw material and fuel ratio and corresponding metallurgical performance parameters; Arranging the generated amount of the mixed ore liquid phase and the corresponding finished sintered ore strength data to generate an original data set; A prediction model is established based on the original data set.

3. The method according to claim 2, wherein The calculation of the amount of liquid phase generated by the mixed ore based on the raw material fuel ratio and the corresponding metallurgical performance parameters includes: The amount of liquid phase generated by the mixed ore is calculated based on the content of adhered particles, the burnout rate and the amount of dry material in the raw material and fuel ratio.

4. The method according to claim 3, wherein The calculation of the amount of liquid phase generated by the mixed ore based on the content of adhered particles, the burn rate and the amount of dry material in the raw material and fuel ratio includes: The amount of liquid phase generated by the mixed ore is calculated according to formula 1; The formula 1: in, is the amount of mixed ore liquid phase generated, is the dry material amount of each raw material, The content of 0 to 1 mm particles in the raw material, is the burnout rate of each raw fuel in the raw fuel ratio.

5. The method according to claim 2, wherein The step of establishing a prediction model based on the original data set includes: The relationship between liquid phase generation and strength was fitted based on nonlinear regression model; Training and validating the nonlinear regression model according to the original data set; The nonlinear regression model that meets the accuracy requirements after verification is used as the prediction model.

6. The method according to claim 5, wherein Before training and verifying the nonlinear regression model according to the original data set, the method further includes: Performing data cleaning on the original data set; Perform data standardization on the cleaned dataset.

7. The method according to claim 1, wherein The calling of the prediction model to calculate the range of the mixed ore liquid phase generation amount required to achieve the target strength and generating the constraint conditions for the mixed ore liquid phase generation amount include: Calculating the upper limit and lower limit of the amount of mixed ore liquid phase generated required to achieve the target strength according to the prediction model; According to the upper limit value and the lower limit value, generate Formula 2 as a constraint condition; The formula 2: Wherein, A is the lower limit value, B is the upper limit value, is the ratio of each raw material, is the liquid phase composition of each raw material.

8. The method according to claim 1, wherein After generating the optimized sintering ore blending plan based on the constraint conditions, the method further includes: Conducting a cost analysis on the optimized sintering ore blending scheme and generating a cost analysis report; Predicting the performance of the finished sintered ore based on the optimized sintering ore blending scheme and generating a performance evaluation report; Output the optimized sintering ore blending plan and the corresponding cost analysis report and performance evaluation report.

9. A device for sintering and blending ore based on the amount of liquid phase generated by mixing ore, characterized in that: include: The model building module is used to establish a prediction model for the amount of mixed ore liquid phase generated and the strength of the finished sintered ore based on the finished sintered ore strength data corresponding to various sintering ore blending schemes; An indicator determination module is used to determine the intensity indicator to be achieved as the target intensity; A constraint calculation module is used to call the prediction model to calculate the range of mixed ore liquid phase generation required to achieve the target strength and generate constraint conditions for the mixed ore liquid phase generation; A scheme generation module is used to generate an optimized sintering ore matching scheme based on the constraint conditions.

10. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images