Scrap quality prediction method, system, and server

Abstract

The application provides a scrap steel quality prediction method, system and server, relates to the metallurgical technology field, and fully utilizes heat balance and material balance in a smelting process of a steelmaking furnace. An experience model of scrap steel prediction is constructed on the basis of a scrap steel metallurgical mechanism model. Twin support vector regression machines and whale swarm algorithms are combined with production data to realize accurate prediction of required scrap steel quality of a next furnace, so that production efficiency can be greatly improved, and the workload of an operator can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of metallurgical technology, and in particular to a scrap steel quality prediction method, system and server. Background Art

[0002] During the smelting process in steelmaking furnaces, scrap steel can be added to molten iron. By rationally increasing the scrap steel ratio, scrap steel recycling can be promoted, thereby reducing the demand for raw materials and lowering resource consumption. In practice, the amount of scrap steel required for the next furnace is manually calculated in advance, and the scrap steel handling area is notified in advance for stockpiling. This manual calculation requires high-level operational skills and results in high labor costs. Furthermore, due to the numerous steps involved, manual calculation accuracy is difficult to guarantee, often resulting in over- or under-estimation of scrap steel quality, impacting overall smelting progress and molten steel quality. Summary of the Invention

[0003] Although there are some scrap steel quality prediction methods in the prior art, these methods are mainly calculated based on relevant theoretical calculations of material balance and heat balance, without considering the actual production status, and there is also the problem of low prediction accuracy. In view of this, the purpose of the present invention is to provide a scrap steel quality prediction method, system and server. This method fully utilizes the heat balance and material balance in the steelmaking process, and constructs an empirical model for scrap steel prediction based on the scrap steel metallurgical mechanism model. It also uses the twin support vector regression machine and the whale group algorithm combined with production data to accurately predict the scrap steel quality required for the next batch. This can significantly improve production efficiency and reduce the workload of operators, thereby solving the above-mentioned problems existing in the prior art.

[0004] In a first aspect, an embodiment of the present invention provides a method for predicting scrap steel quality, the method comprising:

[0005] Calculate the target endpoint temperature of the steelmaking furnace based on the production parameters of the current heat and the production plan for the next heat, and calculate the molten iron composition and molten iron temperature of the next heat;

[0006] Construct a mechanism model of scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace;

[0007] Determine the production process variables corresponding to the steelmaking furnace through the production parameters, and determine the influencing factor parameters of the scrap steel required by the steelmaking furnace based on the influencing factors corresponding to the production process variables;

[0008] Using the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters, an empirical model of scrap steel quality required by the steelmaking furnace is constructed based on the mechanism model;

[0009] Based on the empirical model, a production sample of the steelmaking furnace is constructed. After predicting and calculating the production sample using the twin support vector regression machine and whale swarm algorithm, the required scrap steel quality of the steelmaking furnace in the next batch is obtained.

[0010] Optionally, the target endpoint temperature of the steelmaking furnace is calculated based on the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, including:

[0011] Determine the temperature parameters of the steelmaking furnace according to the production parameters of the current heat, and determine the corrected temperature of the steelmaking furnace according to the production plan of the next heat;

[0012] Get the liquidus temperature contained in the temperature parameter , superheat of molten steel in tundish , Temperature change from the end of refining to the start of pouring , Temperature changes during refining , Temperature change from steel tapping to refining , and obtain the corrected temperature of the pouring sequence contained in the corrected temperature , Corrected temperature of the steel ladle state , Corrected temperature for pouring time , Corrected temperature of steel tapping process ;

[0013] Using liquidus temperature , superheat of molten steel in tundish , Temperature change from the end of refining to the start of pouring , Temperature changes during refining , Temperature change from steel tapping to refining , Corrected temperature of pouring sequence , Corrected temperature of the steel ladle state , Corrected temperature for pouring time , Corrected temperature of steel tapping process Calculate the target endpoint temperature of a steelmaking furnace ; Among them, the target end temperature Calculated by the following formula: .

[0014] Optionally, calculate the molten iron composition and temperature of the next heat in the steelmaking furnace, including:

[0015] Obtain the station parameters and sample parameters of the molten iron corresponding to the steelmaking furnace under the current heat, and determine the composition and temperature of the molten iron based on the station parameters and sample parameters;

[0016] Determine the tank number and age of the molten iron tank in the steelmaking furnace, store the molten iron in the molten iron tank according to the tank number and age based on the composition and temperature, and obtain the molten iron composition table and molten iron temperature table corresponding to the molten iron tank;

[0017] Based on the production parameters, the molten iron ladle required for the next steelmaking furnace is obtained, and the molten iron composition and molten iron temperature are calculated based on the ladle number and age corresponding to the molten iron ladle and the molten iron composition table and molten iron temperature table.

[0018] Optionally, the step of constructing a mechanism model of scrap steel quality required by the steelmaking furnace based on material balance parameters and heat balance parameters of the steelmaking furnace includes:

[0019] The material balance parameters corresponding to the steelmaking furnace are constructed based on the mass of each element in the molten iron participating in the chemical reaction, the mass of oxygen consumed by oxidation and the mass of the product, the mass of the slag-making agent and its components, the mass of the total iron in the final slag, the mass of the final slag and the mass of its components, the total volume of furnace gas and the yield of molten steel.

[0020] Determine the heat input parameters based on the physical heat of molten iron and element oxidation heat corresponding to the steelmaking furnace, and determine the heat expenditure parameters based on the physical heat of molten steel, slag physical heat, other physical heat, magnesium ball decomposition heat, ore decomposition endothermic heat, heat loss, and heat expenditure when there is no scrap steel corresponding to the steelmaking furnace. Then, determine the heat balance parameters corresponding to the steelmaking furnace based on the heat input parameters and heat expenditure parameters;

[0021] A mechanism model of the scrap steel mass required for the steelmaking furnace is constructed using the material balance conditions determined by the material balance parameters and the heat balance conditions determined by the heat balance parameters; wherein the mechanism model is used to calculate the required scrap steel mass based on the difference between the heat income corresponding to the scrap steel absorption and the heat expenditure corresponding to the absence of scrap steel.

[0022] Optionally, the step of determining a production process variable corresponding to the steelmaking furnace through production parameters, and determining an influencing factor parameter of scrap steel required by the steelmaking furnace based on an influencing factor corresponding to the production process variable, includes:

[0023] Determine the influencing conditions of the required scrap steel quality based on the production parameters, and use the influencing conditions to determine the corresponding production process variables of the steelmaking furnace;

[0024] Determine the influencing factors corresponding to the production process variables based on the influencing conditions, and determine, based on the influencing factors, one or more influencing factors included in the production process variables: target temperature, end-point temperature of the loading furnace, molten iron temperature, molten iron temperature of the loading furnace, silicon percentage content of the molten iron, silicon percentage content of the molten iron of the loading furnace, required pig iron quality, pig iron quality of the loading furnace, required molten iron quality, molten iron quality of the loading furnace, scrap steel quality of the loading furnace, oxygen content at the end-point of the loading furnace, fixed converter charge weight, and required scrap steel quality;

[0025] The influencing factors are used to determine the influencing factor parameters of scrap steel required by the steelmaking furnace.

[0026] Optionally, the step of constructing an empirical model of scrap steel quality required by the steelmaking furnace based on the mechanism model using the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters includes:

[0027] The calculation parameters, standard scrap steel quality and affected tonnage corresponding to the steelmaking furnace are determined based on the target endpoint temperature, molten iron composition, molten iron temperature and influencing factor parameters; wherein the calculation parameters include at least: target temperature, furnace endpoint temperature, molten iron temperature, furnace molten iron temperature, molten iron silicon percentage content, furnace molten iron silicon percentage content, required pig iron quality, furnace pig iron quality, required molten iron quality, furnace molten iron quality, furnace scrap steel quality and furnace endpoint oxygen content; the affected tonnage includes at least: the tonnage a of the impact of each 1 degree change in target temperature on the required scrap steel quality, the tonnage b of the impact of each 1 degree change in molten iron temperature on the required scrap steel quality, the tonnage c of the impact of each 1% change in molten iron silicon percentage content on the required scrap steel quality, the tonnage d of the impact of each 1 ton change in pig iron quality on the required scrap steel quality, and the tonnage e of the impact of each 1 ton change in molten iron quality on the required scrap steel quality; the standard scrap steel quality f is a preset fixed value;

[0028] Based on the mechanism model, an empirical model of the scrap steel quality required for the steelmaking furnace is constructed using the calculation parameters, standard scrap steel quality, and influencing tonnage. The empirical model is used to calculate the required scrap steel quality and the required molten iron quality using the calculation parameters, standard scrap steel quality, and influencing tonnage. The required scrap steel quality is calculated using the following formula:

[0029] Required scrap steel mass = (target temperature - end point temperature of loading furnace) × a + (molten iron temperature - molten iron temperature of loading furnace) × b + (silicon content of molten iron - silicon content of molten iron of loading furnace) × c + (required pig iron mass - pig iron mass of loading furnace) × d + (required pig iron mass - molten iron mass of loading furnace) × e + scrap steel mass of loading furnace + (f - oxygen content of loading furnace end point) / 10 × b;

[0030] The required molten iron mass is calculated using the following formula:

[0031] Required molten iron mass = fixed converter loading mass - required scrap steel mass.

[0032] Optionally, the step of constructing an empirical model of scrap steel quality required by the steelmaking furnace based on the mechanism model using the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters includes:

[0033] The calculation parameters, standard setting values, and affected tonnage corresponding to the steelmaking furnace are determined based on the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters; wherein the calculation parameters include at least: target temperature, molten iron temperature, molten iron silicon percentage content, required pig iron quality, required molten iron quality, and incoming molten iron quality; the standard setting values ​​include at least: standard target temperature, standard molten iron temperature, standard molten iron silicon percentage content, standard pig iron quality, standard molten iron quality, standard scrap steel quality f, and standard endpoint oxygen content; and the affected tonnage includes at least: the tonnage a of the impact of each 1-degree change in target temperature on the required scrap steel quality, the tonnage b of the impact of each 1-degree change in molten iron temperature on the required scrap steel quality, the tonnage c of the impact of each 1% change in molten iron silicon percentage content on the required scrap steel quality, the tonnage d of the impact of each 1-ton change in pig iron quality on the required scrap steel quality, and the tonnage e of the impact of each 1-ton change in molten iron quality on the required scrap steel quality;

[0034] An empirical model of the scrap steel quality required for a steelmaking furnace is constructed based on the mechanism model and using the calculation parameters, standard setting values, and influencing tonnage. The empirical model is used to calculate the required scrap steel quality using the calculation parameters, standard setting values, and influencing tonnage. The required scrap steel quality is calculated using the following formula:

[0035] Required scrap steel mass = (target temperature - standard target temperature) × a + (molten iron temperature - standard molten iron temperature) × b + (molten iron silicon percentage content - standard molten iron silicon percentage content) × c + (required pig iron mass - standard pig iron mass) × d + (required molten iron mass - standard molten iron mass) × e + standard scrap steel mass + (f - standard endpoint oxygen content) / 10 × b; among which, the standard target temperature is 1650-1750℃, the standard molten iron temperature is 1200-1300℃, the standard molten iron silicon percentage content is 0.3%-0.5%, the standard pig iron mass is 0.01-0.03 tons, the standard molten iron mass is 175-185 tons, the standard scrap steel mass is 25-40 tons, and the standard endpoint oxygen content is 450-550ppm.

[0036] Optionally, the steps of constructing a production sample of the steelmaking furnace based on the empirical model, and performing prediction calculations on the production sample using a twin support vector regression machine and a whale swarm algorithm to obtain the required scrap steel quality of the steelmaking furnace in the next heat include:

[0037] Use the required scrap steel quality and its corresponding production parameters output by the empirical model to construct a production sample corresponding to the steelmaking furnace;

[0038] A scrap steel quality prediction model for the next batch of production samples is constructed based on the twin support vector regression mechanism, and the temperature error value corresponding to the required scrap steel quality prediction model is calculated using the preset whale group algorithm.

[0039] After predicting and calculating the production samples based on the temperature error value, the required scrap steel quality of the steelmaking furnace in the next batch is obtained.

[0040] In a second aspect, the present invention provides a scrap steel quality prediction system, the system comprising:

[0041] An initialization module is used to calculate the target endpoint temperature of the steelmaking furnace based on the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, and to calculate the molten iron composition and molten iron temperature of the steelmaking furnace in the next heat;

[0042] A mechanism model building module is used to build a mechanism model of the scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace;

[0043] An influencing factor determination module is used to determine the production process variables corresponding to the steelmaking furnace through the production parameters, and determine the influencing factor parameters of the scrap steel required by the steelmaking furnace based on the influencing factors corresponding to the production process variables;

[0044] An empirical model building module is used to build an empirical model of scrap steel quality required by the steelmaking furnace based on the mechanism model using the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters;

[0045] The scrap steel quality prediction module is used to construct production samples of the steelmaking furnace based on the empirical model, and use the twin support vector regression machine and whale group algorithm to predict and calculate the production samples to obtain the required scrap steel quality of the steelmaking furnace in the next batch.

[0046] In a third aspect, an embodiment of the present invention further provides a server comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of the scrap steel quality prediction method provided in the first aspect.

[0047] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the steps of the scrap steel quality prediction method provided in the first aspect.

[0048] An embodiment of the present invention provides a scrap steel quality prediction method, system and server. In the process of predicting the scrap steel quality in the smelting production process of a steelmaking furnace, the method first calculates the target endpoint temperature of the steelmaking furnace based on the production parameters of the current furnace corresponding to the steelmaking furnace and the production plan of the next furnace, and calculates the molten iron composition and molten iron temperature of the steelmaking furnace in the next furnace; then constructs a mechanism model of the scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace; then determines the production process variables corresponding to the steelmaking furnace through the production parameters, and determines the influencing factor parameters of the scrap steel required by the steelmaking furnace based on the influencing factors corresponding to the production process variables; then uses the target endpoint temperature, molten iron composition, molten iron temperature and influencing factor parameters, and constructs an empirical model of the scrap steel quality required by the steelmaking furnace based on the mechanism model; finally, constructs a production sample of the steelmaking furnace based on the empirical model, and uses the twin support vector regression machine and the whale group algorithm to predict and calculate the production sample to obtain the scrap steel quality required by the steelmaking furnace in the next furnace. This method makes full use of the heat balance and material balance in the smelting process of the steelmaking furnace, and constructs an empirical model for scrap steel prediction based on the scrap steel metallurgical mechanism model. It also uses the twin support vector regression machine and whale swarm algorithm combined with production data to achieve accurate prediction of the scrap steel quality required for the next batch. It can greatly improve production efficiency and reduce the workload of operators. It has outstanding substantive characteristics and significant technological progress.

[0049] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 A flowchart of a scrap steel quality prediction method provided by an embodiment of the present invention;

[0053] Figure 2A flowchart of calculating the target endpoint temperature of a steelmaking furnace according to the production parameters of the current heat and the production plan for the next heat in step S101 of a scrap steel quality prediction method provided by an embodiment of the present invention;

[0054] Figure 3 A flowchart of calculating the composition and temperature of molten iron in the next heat of a steelmaking furnace in step S101 of a scrap steel quality prediction method provided by an embodiment of the present invention;

[0055] Figure 4 This is a flowchart of step S102 of a scrap steel quality prediction method provided by an embodiment of the present invention;

[0056] Figure 5 A flowchart of step S103 of a scrap steel quality prediction method provided by an embodiment of the present invention;

[0057] Figure 6 A flowchart of step S104 in a scrap steel quality prediction method provided in an embodiment of the present invention;

[0058] Figure 7 A flowchart of step S104 in another scrap steel quality prediction method provided by an embodiment of the present invention;

[0059] Figure 8 A flowchart of step S105 in a scrap steel quality prediction method provided in an embodiment of the present invention;

[0060] Figure 9 A schematic diagram of the principle of scrap steel quality prediction in a scrap steel quality prediction method provided by an embodiment of the present invention;

[0061] Figure 10 A flowchart of another scrap steel quality prediction method provided by an embodiment of the present invention;

[0062] Figure 11 A schematic structural diagram of a scrap steel quality prediction system provided by an embodiment of the present invention;

[0063] Figure 12 A schematic diagram of the structure of a server provided in an embodiment of the present invention.

[0064] icon:

[0065] 1110-initialization module; 1120-mechanism model construction module; 1130-influencing factor determination module; 1140-empirical model construction module; 1150-scrap quality prediction module;

[0066] 101 - processor; 102 - memory; 103 - bus; 104 - communication interface. DETAILED DESCRIPTION

[0067] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0068] During the smelting process in steelmaking furnaces, scrap steel can be added to molten iron. By properly increasing the scrap ratio, scrap steel recycling can be promoted, reducing raw material demand and lowering resource consumption. Different types of scrap steel, such as carbon content and impurity content, affect the scrap ratio. For example, excessive use of high-carbon scrap steel can increase the oxide content in the slag, reducing slag fluidity and impacting the steelmaking process. Therefore, the appropriate scrap steel quantity must be calculated based on the molten iron conditions and the converter's smelting goals, which is a complex calculation. In practice, the scrap steel quantity required for the next furnace is primarily calculated manually in advance, and the scrap steel handling area is notified in advance for stock preparation. This manual calculation requires high-level operational skills and high labor costs. Furthermore, due to the numerous steps involved, manual calculation accuracy is difficult to guarantee. Consequently, over- or under-predictions of scrap steel quality are common, impacting overall smelting progress and molten steel quality, resulting in low prediction accuracy.

[0069] Based on this, the present invention provides a scrap steel quality prediction method, system and server. The method makes full use of the heat balance and material balance in the smelting process of the steelmaking furnace, and constructs an empirical model for scrap steel prediction based on the scrap steel metallurgical mechanism model. It also uses the twin support vector regression machine and the whale group algorithm combined with production data to realize the accurate prediction of the scrap steel quality required for the next batch, which can greatly improve production efficiency and reduce the workload of operators, thereby solving the above-mentioned problems existing in the prior art.

[0070] To facilitate understanding of this embodiment, a scrap steel quality prediction method disclosed in an embodiment of the present invention is first described in detail. Figure 1 As shown, the method includes:

[0071] Step S101: Calculate the target endpoint temperature of the steelmaking furnace according to the production parameters of the current heat and the production plan of the next heat, and calculate the molten iron composition and molten iron temperature of the next heat.

[0072] The main purpose of this step is to calculate the target endpoint temperature during the current heat production process based on the next heat production plan and predict the next heat's molten iron composition and temperature. In specific implementation, the target endpoint temperature to be achieved during the next steelmaking process is accurately calculated by combining the actual production parameters of the current heat and the next heat production plan. Simultaneously, the composition and initial temperature of the molten iron used in the next heat are analyzed and determined. These parameters serve as the basis for subsequent scrap quality calculations.

[0073] Step S102: constructing a mechanism model of scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace.

[0074] This step primarily builds a mechanistic model for calculating the scrap mass required by the steelmaking furnace, based on the principles of material and heat balance in the steelmaking process. Material balance primarily considers the balance between the input and output of various materials (molten iron, scrap, slag-forming agents, etc.) during the steelmaking process, ensuring element conservation. Heat balance focuses on the relationship between heat sources (such as physical heat from the molten iron and heat released by chemical reactions) and heat consumption (such as heat from scrap heating and heat absorption from slag formation) during the smelting process. Through these two types of balances, a mathematical relationship is theoretically established between scrap mass and other smelting parameters.

[0075] Step S103: determining the production process variables corresponding to the steelmaking furnace through the production parameters, and determining the influencing factor parameters of the scrap steel required by the steelmaking furnace based on the influencing factors corresponding to the production process variables.

[0076] This step screens out the production process variables that affect the quality of scrap steel based on the actual production parameters of the steelmaking furnace. Then, through data analysis or process experience, the influencing factors corresponding to each production process variable (that is, the degree and direction of the variable's influence on the quality of scrap steel) are determined, and these influencing factors are integrated into specific influencing factor parameters to provide a basis for subsequent model optimization.

[0077] Step S104: using the target endpoint temperature, molten iron composition, molten iron temperature and influencing factor parameters, and based on the mechanism model, constructing an empirical model of the scrap steel quality required by the steelmaking furnace.

[0078] The target endpoint temperature, molten iron composition, and molten iron temperature obtained in step S101 are combined with the influencing factor parameters determined in step S103 and substituted into the mechanism model constructed in step S102. The model parameters are further optimized and modified, ultimately constructing an empirical model for the scrap quality required by the steelmaking furnace. This model retains the theoretical basis of the mechanism model while incorporating empirical data from actual production, more accurately reflecting the relationship between scrap quality and various parameters.

[0079] Step S105: construct a production sample of the steelmaking furnace based on the empirical model, and use the twin support vector regression machine and whale swarm algorithm to perform predictive calculations on the production sample to obtain the required scrap steel quality of the steelmaking furnace in the next batch.

[0080] Based on the empirical model constructed in step S104, historical production data is collected to generate a large number of steelmaking production samples (including matching data between various parameters and corresponding scrap quality). These samples are then trained using a Twin Support Vector Regression (TSVR) machine. The Whale Optimization Algorithm (WOA) is then used to optimize key model parameters to improve prediction accuracy. Ultimately, the optimized model calculates the scrap quality required by the steelmaking furnace for the next heat.

[0081] Optionally, the target end temperature of the steelmaking furnace is calculated based on the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, such as Figure 2 Shown, including:

[0082] Step S201: determining the temperature parameters corresponding to the steelmaking furnace according to the production parameters of the current heat of the steelmaking furnace, and determining the corrected temperature corresponding to the steelmaking furnace according to the production plan of the next heat;

[0083] Step S202: Obtain the liquidus temperature contained in the temperature parameters , superheat of molten steel in tundish , Temperature change from the end of refining to the start of pouring , Temperature changes during refining , Temperature change from steel tapping to refining , and obtain the corrected temperature of the pouring sequence contained in the corrected temperature , Corrected temperature of the steel ladle state , Corrected temperature for pouring time , Corrected temperature of steel tapping process ;

[0084] Step S203: Using the liquidus temperature , superheat of molten steel in tundish , Temperature change from the end of refining to the start of pouring , Temperature changes during refining , Temperature change from steel tapping to refining , Corrected temperature of pouring sequence , Corrected temperature of the steel ladle state , Corrected temperature for pouring time , Corrected temperature of steel tapping process Calculate the target endpoint temperature of a steelmaking furnace .

[0085] Target endpoint temperature Calculated by the following formula:

[0086] ;in, is the liquidus temperature, ranging from 1450 to 1550°C, preferably 1500°C; is the superheat of molten steel in the tundish, ranging from 10 to 50°C, preferably 30°C; The temperature change from the completion of refining to the start of pouring is in the range of 5 to 30°C, preferably 25°C; is the changing temperature of the refining process, ranging from -50 to 50°C, preferably -10°C; The temperature change from the completion of steel tapping to the refining is in the range of 5-30°C, preferably 25°C; The correction temperature of the pouring sequence ranges from 0 to 30°C, preferably 10°C; The corrected temperature of the steel ladle is in the range of 0 to 30°C, preferably 20°C; The correction temperature for pouring time is in the range of 0-30℃, preferably 25℃; It is the corrected temperature of the steel tapping process, ranging from 0 to 30°C, preferably 25°C.

[0087] In actual scenarios, temperature correction is required after the target endpoint temperature is calculated:

[0088] If the target molten steel is used as the first pouring pot for the next process, add 5-10℃ to the calculated target end temperature;

[0089] When the ladle heat turnover time is between 2.5 and 4 hours, add 3 to 7°C to the calculated target endpoint temperature;

[0090] For ladle cooling and reheating, add 8-12°C to the calculated target endpoint temperature when the ladle heat turnover time is between 4 and 8 hours;

[0091] For newly heated ladle, when the ladle heat turnover time is between 8 and 24 hours, add 8 to 12°C to the calculated target endpoint temperature;

[0092] If the mass of the cold steel is not less than 2.0 tons, add 3-7℃ to the calculated target end temperature;

[0093] In winter, add 3-7°C to the calculated target endpoint temperature;

[0094] The above correction rules can be superimposed on the calculated target endpoint temperature, but the maximum temperature range of the superimposed correction is 13 to 17°C.

[0095] Optionally, calculate the composition and temperature of the molten iron in the next heat of the steelmaking furnace, such as Figure 3 Shown, including:

[0096] Step S301: obtaining the station parameters and sample parameters of the molten iron corresponding to the steelmaking furnace in the current heat, and determining the composition and temperature of the molten iron based on the station parameters and sample parameters;

[0097] Step S302: Determine the tank number and tank age corresponding to the molten iron tank in the steelmaking furnace, store the molten iron in the molten iron tank according to the tank number and tank age based on the composition and temperature, and obtain the molten iron composition table and molten iron temperature table corresponding to the molten iron tank;

[0098] Step S303: Based on the production parameters, the molten iron ladle required for the next steelmaking furnace is obtained, and the molten iron composition and molten iron temperature are calculated based on the ladle number and age corresponding to the molten iron ladle and the molten iron composition table and the molten iron temperature table.

[0099] In practical scenarios, the above steps can predict the next hot metal ladle number and age required for the current converter based on the converter production sequence and the time the hot metal composition message was received. The hot metal composition and temperature can then be read based on the ladle number and age. Specifically, a two- and three-level communication system for the steelmaking process can be established. Based on the received three-level hot metal message, the hot metal composition and temperature for different workstations and sample numbers are stored according to the ladle number and age. The next hot metal ladle number and age required for the current converter can then be predicted based on the converter production sequence and the time the hot metal composition message was received. Based on the predicted ladle number and age, the corresponding hot metal composition and temperature can be read from the hot metal composition table and hot metal temperature table. Hot metal components include hot metal carbon and hot metal sulfur for the carbon-sulfur sample, as well as hot metal silicon, hot metal manganese, and hot metal phosphorus for the full sample.

[0100] Optionally, step S102 of constructing a mechanism model of scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace is as follows: Figure 4 Shown, including:

[0101] Step S401: constructing material balance parameters corresponding to the steelmaking furnace based on the mass of each element in the molten iron of the steelmaking furnace participating in the chemical reaction, the mass of oxygen consumed by oxidation and the mass of the product, the mass of the slag-forming agent and its components, the mass of the total iron in the final slag, the mass of the final slag and the mass of its components, the total volume of furnace gas, and the yield of the molten steel;

[0102] Step S402: Determine heat input parameters based on the physical heat of molten iron and element oxidation heat corresponding to the steelmaking furnace, and determine heat expenditure parameters based on the physical heat of molten steel, slag physical heat, other physical heat, magnesium ball decomposition heat, ore decomposition endotherm, heat loss, and heat expenditure when there is no scrap steel corresponding to the steelmaking furnace. Then, determine heat balance parameters corresponding to the steelmaking furnace based on the heat input parameters and heat expenditure parameters.

[0103] Step S403: Construct a mechanism model of the scrap steel mass required by the steelmaking furnace using the material balance conditions determined by the material balance parameters and the heat balance conditions determined by the heat balance parameters; wherein the mechanism model is used to calculate the required scrap steel mass based on the difference between the heat income corresponding to the scrap steel absorption and the heat expenditure corresponding to the absence of scrap steel.

[0104] The core of the mechanism model, constructed based on the material balance and heat balance parameters of the steelmaking furnace, is to calculate the scrap mass through the heat balance (scrap needs to absorb the "heat surplus when no scrap is added" to achieve heat balance). This can be achieved using the following formula:

[0105] ;

[0106] in, is the mass of scrap steel required by the steelmaking furnace (in tons), which is the output of the mechanism model. is the heat input parameter (kJ) of the steelmaking furnace, which is defined by step S402 and is equal to "physical heat of molten iron + heat of element oxidation" (the sum of the physical heat brought into the molten iron and the heat released by the element oxidation reaction in the molten iron). is the heat expenditure parameter (kJ) when there is no scrap steel, defined by step S402, that is, the total heat consumption when no scrap steel is added, including the sum of the physical heat of molten steel, physical heat of slag, other physical heat, decomposition heat of magnesium balls, heat absorbed by ore decomposition and heat loss. is the specific heat capacity of scrap steel (kJ / (kg•℃)), which represents the amount of heat required to raise the temperature of unit mass of scrap steel by 1℃ (an inherent physical property parameter of scrap steel in material balance). is the temperature change of scrap steel (℃), that is, the temperature difference of scrap steel from the initial temperature to the target end temperature of steelmaking is ,in is the target endpoint temperature T calculated in the previous step, is the initial temperature when scrap steel is added.

[0107] The above steps construct a mechanism model of the required scrap steel quality based on material balance and heat balance. The materials required in the material balance include the mass of each element in the molten iron participating in the chemical reaction, the mass of oxidation oxygen consumption and the mass of the product, the mass of the slag-making agent and its components, the mass of the total iron in the final slag, the mass of the final slag and the mass of its components, the total volume of the furnace gas and the yield of the molten steel; while the heat balance includes heat income and heat expenditure. The heat income includes the physical heat of the molten iron and the heat of element oxidation. The heat expenditure includes the physical heat of the molten steel, the physical heat of the slag, other physical heat, the decomposition heat of magnesium balls, the heat absorption of ore decomposition, heat loss and the heat expenditure when there is no scrap steel. After obtaining the heat absorption of scrap steel as the difference between the heat income and the heat expenditure when no scrap steel is added, the required scrap steel quality is calculated based on the heat balance and material balance and the types of materials that affect the scrap steel quality are determined.

[0108] In the process of obtaining the materials required for the material balance calculation, for the scenario where no scrap steel is added, the data can be processed according to the molten iron composition and molten iron temperature obtained in step S101, combined with the composition of the furnace lining, slag-making agent and the smelting target composition, so as to perform a material balance calculation. Specifically, the final slag basicity R is between 3 and 3.5; the mass of iron bauxite added is 0.3% to 0.6% of the mass of the molten iron; the mass of ore added is 0.9% to 1.1% of the mass of the molten iron; the mass of the furnace lining erosion is calculated as 0.1% to 0.3% of the mass of the molten iron; the final slag T.Fe content is calculated as 11% to 14%, of which the mass of FeO in the slag is 1.25 to 1.45 times the mass of Fe2O3; the mass of smoke is calculated as 1.3% to 1.5% of the mass of the molten iron; the mass of splashing iron loss is calculated as molten iron. The iron loss in the slag is calculated as 0.1% to 0.3% of the slag mass; the iron loss in the slag is calculated as 1% to 2% of the slag mass; the oxygen purity is 99.3% to 99.5% by volume of oxygen and 0.7% to 0.5% by volume of nitrogen; the volume of free oxygen in the furnace gas is taken as 0.3% to 0.5% of the furnace gas volume; the gasification desulfurization mass accounts for 30.1% to 33.4% of the total desulfurization mass; the oxidation of C in the metal is taken as the mass of C oxidized to CO, which accounts for 75% to 80%, and the mass of C oxidized to CO2, which accounts for 25% to 20%.

[0109] The material balance calculation process involves many parameters, which are explained in detail below.

[0110] The mass of each element in the molten iron participating in chemical reactions includes: the carbon content of the molten steel at the end of the smelting process (available through the Level 3 Operations Guide); C represents the carbon content of the molten steel at the end of the smelting process (available through the Level 3 Operations Guide); Si represents the Si in the molten iron that participates in chemical reactions and enters the slag during the basic converter steelmaking process; Mn represents the mass of Mn remaining in the molten steel at the end of the smelting process, which is 50% to 60% of the mass of Mn in the molten iron; P represents a P removal rate of 80% to 85%; and S represents a desulfurization rate of 0 when the molten iron is pretreated for desulfurization in the converter. The above information can be combined to determine the oxidized mass of each element in the molten iron, and the mass of carbon oxidized to carbon monoxide, the mass of carbon oxidized to carbon dioxide, and the mass of S oxidized to SO2 and reduced to CaS can be calculated.

[0111] The oxidation oxygen consumption and product quality of each element contained in the molten iron are shown in Table 1 below.

[0112] Table 1

[0113]

[0114] For the slag-forming agent and its components, the mass of each component can be calculated using the formula based on the mass of the added iron bauxite and ore, the mass of the furnace lining eroded during smelting, and the composition of each component. Among them, the amount of sulfur in the ore participating in the chemical reaction to form calcium sulfide is: kg; the mass of calcium oxide consumed is: kg; the oxidation mass of carbon element in the furnace lining participating in the chemical reaction is: kg; the calculated masses of carbon monoxide and carbon dioxide are 0.031kg and 0.012kg respectively; the mass of calcium sulfide generated by the chemical reaction of sulfur in the bauxite is: kg; the mass of calcium oxide consumed in the reaction and the mass of O2 generated are negligible.

[0115] In addition to adding lime for slag formation, magnesium balls are also added during smelting to increase the magnesium oxide content in the converter slag, which is beneficial for extending the life of the converter lining (refractory). In specific scenarios, the amount of magnesium balls added is 0.3% to 0.6% per 100kg of molten iron. The masses of each component can be calculated using the corresponding formula and will not be detailed here.

[0116] In this embodiment, binary basicity can be used, and R is taken as 3 to 3.5 for calculation. When SiO2 introduced by lime is not taken into account, the mass of silicon dioxide in the slag is calculated as follows:

[0117] ;

[0118] in, In molten iron quality, For furnace lining quality, For ore quality, For iron bauxite quality, For magnesium balls quality;

[0119] The mass of CaO currently contained in the slag is calculated as follows:

[0120] ;

[0121] in, For furnace lining quality, For ore quality, For iron bauxite quality, For magnesium balls quality, Consumption for desulfurization quality;

[0122] The amount of lime added is:

[0123] ;

[0124] Among them, R is the final slag basicity, is the mass of silica present in the slag, is the mass of CaO currently contained in the slag, For lime quality, For lime quality;

[0125] After calculation, it can be obtained that the mass of CaS generated by the reaction of S element in lime and the mass of oxygen consumed and the mass of calcium oxide consumed are 0.004kg. The mass of calcium oxide brought in by lime and the mass of other components brought in by lime can be calculated by combining the mass of lime added and the mass percentage of other components in lime.

[0126] In the process of obtaining the total iron content T.Fe of the final slag, factors such as C at the end point of T.Fe, the end point temperature T and R are related, and the mass of FeO and Fe2O3 can be calculated.

[0127] In the process of obtaining the final slag mass and its composition, when the final slag mass does not include FeO and Fe2O3, the slag mass W s for:

[0128] ;

[0129] in, For the final slag quality, For the final slag quality, is the mass of Al2O3 in the final slag, is the mass of MnO in the final slag, is the mass of P2O5 in the final slag, is the mass of CaS in the final slag, For the final slag quality;

[0130] The amount of iron and oxygen in the furnace lining, slagging agent and flue dust. All iron oxides in the furnace lining and furnace lining are reduced to iron. Based on the material balance, the mass of iron and oxygen brought in by the slagging agent and furnace lining, as well as the mass of iron and oxygen taken away by the converter dust can be calculated.

[0131] The calculation process of the total volume of furnace gas Vg is as follows:

[0132] ;

[0133] in, is the current furnace gas volume, is the percentage of free O in the furnace gas, which is 0.3%-0.5%; The N2 component in O2 is taken as 0.3%-0.5%; It is the O2 component in O2, which is taken as 99.5%-99.6%.

[0134] Regarding the quality of molten steel, the various losses of molten iron during the blowing process are shown in Table 2. Taking 100kg of molten iron as an example, the various losses of molten iron during the blowing process are shown in Kg:

[0135] Table 2

[0136]

[0137] According to Table 2, the mass of molten steel Wm is: ; That is, the recovery rate of molten steel is 93.627%.

[0138] In the heat balance calculation process, the values ​​of the latent heat of fusion or average specific heat capacity of the material are shown in Table 3:

[0139] Table 3

[0140]

[0141] The materials added to the furnace, the product temperature, the composition and temperature of the scrap steel, the thermal effects of each steelmaking reaction, and the thermal effects of each chemical reaction during the steelmaking process are shown in Table 4:

[0142] Table 4

[0143]

[0144] During the heat balance calculation process, the heat input mainly includes the physical heat of molten iron Qhm, the slag heat or oxidation heat of the elements. According to the oxidation amount of each element in the molten iron when participating in the chemical reaction and the thermal effect of the corresponding chemical reaction, the slag heat or oxidation heat of each element in the molten iron participating in the chemical reaction can be calculated. The unit is Kg. The calculation results are shown in Table 5. The oxidation heat of Fe element in the smoke and the oxidation heat of C element in the furnace lining Q1:

[0145] Table 5

[0146]

[0147] Thermal expenditure mainly includes physical heat of molten steel, physical heat of slag, other physical heat, decomposition heat of magnesium balls, heat absorption of ore decomposition, heat loss, and thermal expenditure Q when there is no scrap steel. out , scrap steel absorbs heat Q f It is the difference between the heat income and the heat expenditure when no scrap steel is added. Based on the heat balance and material balance, the mass of scrap steel added is calculated.

[0148] Optionally, the step S103 of determining the production process variables corresponding to the steelmaking furnace by the production parameters and determining the influencing factor parameters of the scrap steel required by the steelmaking furnace based on the influencing factors corresponding to the production process variables is as follows: Figure 5 Shown, including:

[0149] Step S501: determining the influencing conditions of the required scrap steel quality based on the production parameters, and determining the production process variables corresponding to the steelmaking furnace using the influencing conditions.

[0150] First, starting from the basic parameters of steelmaking production (such as steel grade specifications and output requirements), the various conditions that affect the required scrap steel quality (such as temperature control requirements and composition balance requirements) are analyzed and clarified. Then, based on these influencing conditions, the production process variables that need to be monitored and adjusted during the steelmaking furnace production process are further determined.

[0151] Step S502: Determine the influencing factors corresponding to the production process variables according to the influencing conditions, and determine one or more of the influencing factors included in the production process variables, including the target temperature, the end temperature of the furnace, the molten iron temperature, the molten iron temperature of the furnace, the silicon percentage content of the molten iron, the silicon percentage content of the molten iron, the required pig iron quality, the pig iron quality of the furnace, the required molten iron quality, the molten iron quality of the furnace, the scrap steel quality of the furnace, the end oxygen content of the furnace, the fixed loading quality of the converter, and the required scrap steel quality.

[0152] Based on the influencing conditions determined in step S501, the influencing factors behind the production process variables (i.e., the degree of correlation or mechanism of the effect of each variable on the scrap steel quality) are analyzed and clarified; based on these influencing factors, key influencing factors closely related to the scrap steel quality are screened out from the production process variables, which may specifically include one or more of the following: target temperature, end-point temperature of the loading furnace, molten iron temperature, molten iron temperature of the loading furnace, silicon percentage content of the molten iron, silicon percentage content of the molten iron of the loading furnace, required pig iron quality, pig iron quality of the loading furnace, required molten iron quality, molten iron quality of the loading furnace, scrap steel quality of the loading furnace, oxygen content at the end-point of the loading furnace, fixed converter charge mass, and required scrap steel quality.

[0153] Step S503: Determine the influencing factor parameters of the scrap steel required by the steelmaking furnace using the influencing factors.

[0154] The influencing factors screened out in step S502 are further converted into specific, quantifiable parameter indicators to determine the influencing factor parameters of the scrap steel required by the steelmaking furnace during the production process, providing a clear basis for the subsequent selection of scrap steel and optimization of the steelmaking process.

[0155] During the actual implementation process, based on the independence and correlation analysis, the converter production process variables with larger influencing factors are selected to determine the influencing factors of the required scrap steel quality. The influencing factors of the required scrap steel quality include: target temperature, furnace end temperature, molten iron temperature, furnace molten iron temperature, molten iron silicon percentage content, furnace molten iron silicon percentage content, required pig iron quality, furnace pig iron quality, required molten iron quality, furnace molten iron quality, furnace scrap steel quality, furnace end oxygen content, converter fixed loading mass, and required scrap steel quality.

[0156] Optionally, step S104 of constructing an empirical model of scrap steel quality required by the steelmaking furnace based on the mechanism model using the target endpoint temperature, molten iron composition, molten iron temperature and influencing factor parameters is as follows: Figure 6 Shown, including:

[0157] Step S601: determining calculation parameters corresponding to the steelmaking furnace, standard scrap steel mass, and influencing tonnage according to the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters;

[0158] Step S602: constructing an empirical model of the scrap steel quality required for the steelmaking furnace based on the mechanism model and using calculation parameters, standard scrap steel quality and influencing tonnage; wherein the empirical model is used to calculate the required scrap steel quality and the required molten iron quality through calculation parameters, standard scrap steel quality and influencing tonnage.

[0159] The calculation parameters include at least: target temperature, end-of-furnace temperature, molten iron temperature, molten iron temperature, molten iron silicon percentage, molten iron silicon percentage, required pig iron quality, pig iron quality, required molten iron quality, molten iron quality, scrap quality, and end-of-furnace oxygen content. The impact tonnage includes at least: the impact a of a 1°C change in target temperature on the required scrap quality, b of a 1°C change in molten iron temperature on the required scrap quality, c of a 1% change in molten iron silicon percentage on the required scrap quality, d of a 1% change in pig iron quality on the required scrap quality, and e of a 1% change in molten iron quality on the required scrap quality. The standard scrap quality f is a preset fixed value.

[0160] The required scrap steel mass is calculated using the following formula:

[0161] Required scrap steel mass = (target temperature - end point temperature of loading furnace) × a + (molten iron temperature - molten iron temperature of loading furnace) × b + (silicon content of molten iron - silicon content of molten iron of loading furnace) × c + (required pig iron mass - pig iron mass of loading furnace) × d + (required pig iron mass - molten iron mass of loading furnace) × e + scrap steel mass of loading furnace + (f - oxygen content of loading furnace end point) / 10 × b;

[0162] The required molten iron mass is calculated using the following formula: Required molten iron mass = fixed converter charge mass - required scrap steel mass.

[0163] In the above formula, the range of a is -0.110 to -0.210 tons, preferably -0.112 tons; the range of b is 0.110 to 0.210 tons, preferably 0.200 tons; the range of c is 3.55 to 3.95 tons, preferably 3.55 tons; the range of d is 0.3 to 0.7 tons, preferably 0.4 tons; the range of e is 0.355 to 0.395 tons, preferably 0.375 tons; the range of f is 20 to 50 tons, preferably 30 tons.

[0164] When any value in the previous furnace information is missing, the following implementation method is calculated. Optionally, the target endpoint temperature, molten iron composition, molten iron temperature and influencing factor parameters are used to construct an empirical model of the scrap steel quality required by the steelmaking furnace based on the mechanism model S104, such as Figure 7 Shown, including:

[0165] Step S701: determining calculation parameters, standard setting values, and influencing tonnage corresponding to the steelmaking furnace according to the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters;

[0166] Step S702: constructing an empirical model of the scrap steel quality required for the steelmaking furnace based on the mechanism model and using calculation parameters, standard setting values ​​and influencing tonnage; wherein the empirical model is used to calculate the required scrap steel quality through calculation parameters, standard setting values ​​and influencing tonnage.

[0167] Among them, the calculation parameters include at least: target temperature, molten iron temperature, molten iron silicon percentage content, required pig iron quality, required molten iron quality, and molten iron quality on the furnace; the standard setting values ​​include at least: standard target temperature, standard molten iron temperature, standard molten iron silicon percentage content, standard pig iron quality, standard molten iron quality, standard scrap steel quality f, and standard endpoint oxygen content; the affected tonnage includes at least: the tonnage a of the impact of each 1 degree change in target temperature on the required scrap steel quality, the tonnage b of the impact of each 1 degree change in molten iron temperature on the required scrap steel quality, the tonnage c of the impact of each 1% change in molten iron silicon percentage content on the required scrap steel quality, the tonnage d of the impact of each 1 ton change in pig iron quality on the required scrap steel quality, and the tonnage e of the impact of each 1 ton change in molten iron quality on the required scrap steel quality.

[0168] The required scrap steel mass is calculated using the following formula:

[0169] Required scrap steel mass = (target temperature - standard target temperature) × a + (molten iron temperature - standard molten iron temperature) × b + (molten iron silicon percentage - standard molten iron silicon percentage) × c + (required pig iron mass - standard pig iron mass) × d + (required molten iron mass - standard molten iron mass) × e + standard scrap steel mass + (f - standard endpoint oxygen content) / 10 × b;

[0170] Among them, the standard target temperature is 1650-1750°C, preferably 1650°C; the standard molten iron temperature is 1200-1300°C, preferably 1200°C; the standard molten iron silicon content is 0.3%-0.5%, preferably 0.5%; the standard pig iron mass is 0.01-0.03 tons, preferably 0.01 ton; the standard molten iron mass is 175-185 tons, preferably 175 tons; the standard scrap steel mass is 25-40 tons, preferably 25 tons; the standard endpoint oxygen content is 450-550ppm, preferably 450ppm.

[0171] In actual scenarios, the scrap steel mass calculated according to the above steps needs to be corrected according to the following situations:

[0172] Steel grades with a target molten steel phosphorus content of less than 0.015% are low-phosphorus steels. When the steel grade group is low-phosphorus steel, the required scrap steel mass needs to be subtracted by 5 tons on the basis of the calculated result. Steel grades with a target molten steel phosphorus content of greater than 0.026% are high-phosphorus steels. When the steel grade group is high-phosphorus steel, the required scrap steel mass needs to be added by 3 tons on the basis of the calculated result.

[0173] The production mode in which the mass of molten iron required to produce 1 ton of molten steel is less than 0.93 tons is the low iron consumption mode. When the iron consumption mode is low iron consumption, the required scrap steel mass is first calculated using the empirical model, and then the required scrap steel mass = fixed converter loading mass * scrap steel mass content percentage is used for calculation. The largest value of the two is taken as the optimal required scrap steel mass value.

[0174] Optionally, a production sample of the steelmaking furnace is constructed based on the empirical model, and after predicting and calculating the production sample using the twin support vector regression machine and the whale group algorithm, the step S105 of obtaining the scrap steel quality required for the next batch of the steelmaking furnace is performed. Figure 8 Shown, including:

[0175] Step S801: constructing a production sample corresponding to a steelmaking furnace using the required scrap steel quality and its corresponding production parameters output by the empirical model;

[0176] Step S802: constructing a scrap steel quality prediction model required for the next heat corresponding to the production sample based on the twin support vector regression mechanism, and calculating the temperature error value corresponding to the required scrap steel quality prediction model using the preset whale group algorithm;

[0177] Step S803: After performing a prediction calculation on the production sample based on the temperature error value, the required scrap steel quality of the steelmaking furnace in the next heat is obtained.

[0178] The smelting process of the converter can be regarded as a complex nonlinear system, so the method of approximating nonlinear functions can be used, combined with the smelting data of the converter, through data training, that is, adjusting the weights and thresholds of the network, and finally obtaining the scrap steel prediction model of the converter smelting process. The neural network is based on the model of input and output data. During the modeling process, there is no need to care about the reaction mechanism of the blowing process. The approximation of the nonlinear system is achieved through data and has been applied in steel metallurgy; the support vector machine algorithm is based on the dimension theory and the principle of structural risk minimization in statistical theory. It uses limited sample information to find the best match between the complexity of the model and the learning ability. The modeling process is different from that of the neural network. The objective function of the support vector machine is a quadratic programming problem, so there must be a global optimal solution to this problem, and the generalization ability of the model is also better than the neural network model; with the introduction of the twin support vector machine algorithm, the modeling efficiency and accuracy of the model have been further improved, and it is suitable for the study of classification and regression problems; the twin support vector regression machine TSVR model can solve local minimization problems and has high model update efficiency.

[0179] The Whale Swarm Algorithm (WOA) is a new heuristic optimization algorithm that mimics the hunting behavior of humpback whales. In the WOA algorithm, the position of each humpback represents a feasible solution. Humpback whales have a unique hunting method in their ocean activities. Based on an empirical model and production data corresponding to production parameters, 800 furnace production samples were obtained. A scrap quality prediction model based on WOA and TSVR was then used to predict scrap quality in real time.

[0180] Combining the modeling details of the Twin Support Vector Regression (TSVR), the optimization process of the Whale Swarm Algorithm (WOA), and the characteristic dimensions of the production samples, the quality prediction result of the next batch of scrap steel can be achieved using the following formula:

[0181] ;

[0182] Among them, the dual hyperplane output of the TSVR model is and , TSVR approximates the nonlinear relationship by constructing two hyperplanes, and its training process satisfies:

[0183] ;

[0184] Specifically, : Upper hyperplane output (TSVR's upper limit prediction of scrap steel quality); : Lower hyperplane output (TSVR’s lower limit prediction of scrap steel quality);

[0185] : 9-dimensional production feature vector (from 800 furnace samples);

[0186] For kernel function mapping (such as RBF kernel , is the kernel parameter);

[0187] is the hyperplane normal vector; is the bias term; is the slack variable (allowable error);

[0188] is the penalty factor (control for exceeding the error the penalty intensity of the sample);

[0189] Output of the empirical model for the i-th furnace sample is the scrap mass (in tons).

[0190] This is the temperature error correction term optimized by WOA. WOA optimizes the temperature error correction by simulating humpback whale hunting behavior (encirclement, bubble net, random search). Its goal is to:

[0191] ;

[0192] in, : TSVR predicted value of the endpoint temperature of the i-th furnace is the weight coefficient, ); is the actual endpoint temperature of the i-th furnace; the objective function is the mean square error (MSE) of 800 furnace samples, is the optimal temperature correction to minimize the MSE.

[0193] is the temperature-scrap conversion coefficient, specifically, Its physical meaning is the scrap steel mass adjustment amount corresponding to unit temperature deviation (tons / °C), which is calculated by the average ratio of "actual scrap steel mass deviation" to "temperature deviation" in the historical data of 800 furnaces.

[0194] The logic of the above process is: TSVR passes through the double hyperplane ( , ) Fit the nonlinear relationship of 800 furnace production samples and take the mean of the two as the basic prediction value; WOA optimizes the temperature error correction , compensate for the temperature prediction deviation of TSVR; use the conversion coefficient k to convert the temperature correction amount into the scrap steel quality correction value, and superimpose it with the TSVR basic prediction value to obtain the final prediction result The above process fully embodies the core mechanism of double hyperplane nonlinear regression (TSVR) + optimization error compensation (WOA), which is adapted to the prediction requirements of the complex nonlinear smelting process of the converter.

[0195] like Figure 9 The principle diagram of scrap steel quality prediction shown in the figure first uses the twin support vector regression machine prediction model to establish the scrap steel quality prediction model required for the next furnace, and then uses the whale optimization algorithm to optimize the required scrap steel quality. The relationship between the temperature output value and the target value is optimized according to the principle of minimum error, and then the optimal required scrap steel quality result is output.

[0196] like Figure 10 The flowchart of another scrap steel quality prediction method shown is that the overall technical route is to establish an empirical model for scrap steel prediction based on the heat balance and material balance in the converter smelting process and the scrap steel metallurgical mechanism model. Based on WOA and TSVR, production big data is used, combined with on-site production processes, to accurately predict the scrap steel quality required for the next furnace plan in real time for different smelting conditions.

[0197] During the specific implementation process, a three-level production plan communication and molten iron composition and temperature information communication interface can be established in the data preparation stage; then, the converter smelting process is analyzed based on the material balance and heat balance, and the quality of the next batch of scrap steel is calculated; data is preprocessed using on-site production data, and the input items of the empirical model for predicting scrap steel quantity are determined through independence and correlation analysis to ensure model accuracy; based on the empirical model, available data suitable for training are accumulated, and the support vector machine regression algorithm based on the whale group algorithm is used to predict the quality of the next batch of scrap steel.

[0198] It can be seen from the scrap steel quality prediction method in the above embodiment that this method makes full use of the heat balance and material balance in the smelting process of the steelmaking furnace, and constructs an empirical model for scrap steel prediction based on the scrap steel metallurgical mechanism model, and uses the twin support vector regression machine and whale group algorithm combined with production data to achieve accurate prediction of the scrap steel quality required for the next batch, which can greatly improve production efficiency and reduce the workload of operators.

[0199] Corresponding to the above-mentioned scrap steel quality prediction method embodiment, the embodiment of the present invention also provides a scrap steel quality prediction system, such as Figure 11 As shown, the system includes:

[0200] Initialization module 1110, for calculating the target endpoint temperature of the steelmaking furnace based on the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, and calculating the molten iron composition and molten iron temperature of the next heat of the steelmaking furnace;

[0201] A mechanism model building module 1120 is used to build a mechanism model of scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace;

[0202] An influencing factor determination module 1130 is configured to determine a production process variable corresponding to the steelmaking furnace through production parameters, and determine an influencing factor parameter of scrap steel required by the steelmaking furnace based on the influencing factors corresponding to the production process variables;

[0203] An empirical model building module 1140 is used to build an empirical model of scrap steel quality required by the steelmaking furnace based on the mechanism model using the target endpoint temperature, molten iron composition, molten iron temperature, and influencing factor parameters;

[0204] The scrap steel quality prediction module 1150 is used to construct a production sample of the steelmaking furnace based on the empirical model, and use the twin support vector regression machine and the whale group algorithm to predict and calculate the production sample to obtain the required scrap steel quality of the steelmaking furnace in the next batch.

[0205] From the above scrap steel quality prediction system, it can be seen that the system makes full use of the heat balance and material balance in the smelting process of the steelmaking furnace, and constructs an empirical model for scrap steel prediction based on the scrap steel metallurgical mechanism model. It also uses the twin support vector regression machine and whale swarm algorithm combined with production data to achieve accurate prediction of the scrap steel quality required for the next batch, which can greatly improve production efficiency and reduce the workload of operators.

[0206] The scrap steel quality prediction system provided in the embodiment of the present invention has the same implementation principle and technical effects as those in the aforementioned scrap steel quality prediction method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference can be made to the corresponding content in the aforementioned scrap steel quality prediction method embodiment.

[0207] This embodiment also provides a server, the structural diagram of which is as follows: Figure 12 As shown, the device includes a processor 101 and a memory 102; wherein the memory 102 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the steps of the above-mentioned scrap steel quality prediction method.

[0208] Figure 12 The server shown further includes a bus 103 and a communication interface 104 , and the processor 101 , the communication interface 104 and the memory 102 are connected via the bus 103 .

[0209] The memory 102 may include a high-speed random access memory (RAM) and may also include a non-volatile memory, such as at least one disk storage. The bus 103 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 12 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0210] The communication interface 104 is used to connect to at least one user terminal and other network units through a network interface, and send the encapsulated IPv4 message or IPv4 message to the user terminal through the network interface.

[0211] The processor 101 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 101 or by instructions in the form of software. The above-mentioned processor 101 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 102, and processor 101 reads information in memory 102 and, in conjunction with its hardware, completes the steps of the method of the aforementioned embodiment.

[0212] An embodiment of the present invention further provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for predicting scrap steel quality in the aforementioned embodiment are executed.

[0213] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, equipment and methods can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0214] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0215] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0216] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0217] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for predicting scrap steel quality, characterized in that: The method comprises: Calculating the target endpoint temperature of the steelmaking furnace according to the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, and calculating the molten iron composition and molten iron temperature of the steelmaking furnace in the next heat; Constructing a mechanism model of scrap steel quality required by the steelmaking furnace based on material balance parameters and heat balance parameters of the steelmaking furnace; Determining a production process variable corresponding to the steelmaking furnace through the production parameter, and determining an influencing factor parameter of scrap steel required by the steelmaking furnace based on an influencing factor corresponding to the production process variable; Using the target endpoint temperature, the molten iron composition, the molten iron temperature, and the influencing factor parameters, and based on the mechanism model, an empirical model of the scrap steel quality required by the steelmaking furnace is constructed; Constructing a production sample of the steelmaking furnace based on the empirical model, and performing prediction calculations on the production sample using a twin support vector regression machine and a whale swarm algorithm to obtain the scrap steel quality required for the next heat of the steelmaking furnace; Calculating the target endpoint temperature of the steelmaking furnace according to the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, including: Determining the temperature parameters corresponding to the steelmaking furnace according to the production parameters of the steelmaking furnace in the current heat, and determining the corrected temperature corresponding to the steelmaking furnace according to the production plan of the next heat; Get the liquidus temperature contained in the temperature parameters , superheat of molten steel in tundish , Temperature change from the end of refining to the start of pouring , Temperature changes during refining , Temperature change from steel tapping to refining , and obtain the correction temperature of the pouring order contained in the correction temperature , Corrected temperature of the steel ladle state , Corrected temperature for pouring time , Corrected temperature of steel tapping process ; Using the liquidus temperature , the superheat of the molten steel in the tundish , the temperature change from the completion of refining to the start of pouring , the changing temperature of the refining process , the temperature change from the completion of steel tapping to the refining , the corrected temperature of the pouring sequence , the corrected temperature of the steel ladle state , the corrected temperature of the pouring time , the corrected temperature of the steel tapping process Calculate the target endpoint temperature of the steelmaking furnace ; Wherein, the target endpoint temperature Calculated by the following formula: ; Calculating the composition and temperature of the molten iron in the next heat of the steelmaking furnace includes: Obtaining the station parameters and sample parameters of the molten iron corresponding to the steelmaking furnace in the current heat, and determining the composition and temperature of the molten iron based on the station parameters and the sample parameters; determining a tank number and a tank age corresponding to a molten iron tank in the steelmaking furnace, storing the molten iron in the molten iron tank according to the tank number and the tank age based on the composition and the temperature, and obtaining a molten iron composition table and a molten iron temperature table corresponding to the molten iron tank; The molten iron tank required by the steelmaking furnace for the next batch is obtained based on the production parameters, and the molten iron composition and the molten iron temperature are calculated based on the tank number and the tank age corresponding to the molten iron tank and based on the molten iron composition table and the molten iron temperature table.

2. The scrap steel quality prediction method according to claim 1, characterized in that: The step of constructing a mechanism model of the scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace comprises: The material balance parameters corresponding to the steelmaking furnace are constructed based on the mass of each element in the molten iron of the steelmaking furnace participating in the chemical reaction, the mass of oxygen consumed by oxidation and the mass of the product, the mass of the slag-forming agent and its components, the mass of the total iron in the final slag, the mass of the final slag and the mass of its components, the total volume of furnace gas and the yield of molten steel. Determining a heat income parameter according to the physical heat of molten iron and element oxidation heat corresponding to the steelmaking furnace, and determining a heat expenditure parameter according to the physical heat of molten steel, slag physical heat, other physical heat, magnesium ball decomposition heat, ore decomposition endothermic heat, heat loss, and heat expenditure when there is no scrap steel corresponding to the steelmaking furnace, and then determining the heat balance parameter corresponding to the steelmaking furnace based on the heat income parameter and the heat expenditure parameter; A mechanism model of the scrap steel mass required for the steelmaking furnace is constructed using the material balance conditions determined by the material balance parameters and the heat balance conditions determined by the heat balance parameters; wherein the mechanism model is used to calculate the required scrap steel mass based on the difference between the heat income corresponding to the scrap steel absorption and the heat expenditure corresponding to when no scrap steel is added.

3. The scrap steel quality prediction method according to claim 1, characterized in that: The step of determining a production process variable corresponding to the steelmaking furnace by using the production parameter, and determining an influencing factor parameter of scrap steel required by the steelmaking furnace based on an influencing factor corresponding to the production process variable, comprises: Determining influencing conditions of the required scrap steel quality based on the production parameters, and determining production process variables corresponding to the steelmaking furnace using the influencing conditions; Determine the influencing factors corresponding to the production process variables according to the influencing conditions, and determine, based on the influencing factors, one or more influencing factors included in the production process variables: target temperature, end-point temperature of the loading furnace, molten iron temperature, molten iron temperature of the loading furnace, silicon percentage content of molten iron, silicon percentage content of molten iron of the loading furnace, required pig iron quality, pig iron quality of the loading furnace, required molten iron quality, molten iron quality of the loading furnace, scrap steel quality of the loading furnace, oxygen content at the end-point of the loading furnace, fixed converter charge quality, and required scrap steel quality; The influencing factors are used to determine the influencing factor parameters of the scrap steel required by the steelmaking furnace.

4. The method for predicting scrap steel quality according to claim 1, wherein: The step of constructing an empirical model of scrap steel quality required by the steelmaking furnace based on the mechanism model using the target endpoint temperature, the molten iron composition, the molten iron temperature, and the influencing factor parameters includes: The calculation parameters, standard scrap steel quality and affected tonnage corresponding to the steelmaking furnace are determined according to the target endpoint temperature, the molten iron composition, the molten iron temperature and the influencing factor parameters; wherein the calculation parameters include at least: target temperature, upper furnace endpoint temperature, molten iron temperature, upper furnace molten iron temperature, molten iron silicon percentage content, upper furnace molten iron silicon percentage content, required pig iron quality, upper furnace pig iron quality, required molten iron quality, upper furnace molten iron quality, upper furnace scrap steel quality and upper furnace endpoint oxygen content; the affected tonnage includes at least: the tonnage a of the impact of each 1 degree change in target temperature on the required scrap steel quality, the tonnage b of the impact of each 1 degree change in molten iron temperature on the required scrap steel quality, the tonnage c of the impact of each 1% change in molten iron silicon percentage content on the required scrap steel quality, the tonnage d of the impact of each 1 ton change in pig iron quality on the required scrap steel quality, and the tonnage e of the impact of each 1 ton change in molten iron quality on the required scrap steel quality; the standard scrap steel quality f is a preset fixed value; An empirical model of the scrap steel quality required for the steelmaking furnace is constructed based on the mechanism model and using the calculation parameters, the standard scrap steel quality, and the impact tonnage; wherein the empirical model is used to calculate the required scrap steel quality and the required molten iron quality using the calculation parameters, the standard scrap steel quality, and the impact tonnage; wherein the required scrap steel quality is calculated using the following formula: Required scrap steel mass = (target temperature - end point temperature of loading furnace) × a + (molten iron temperature - molten iron temperature of loading furnace) × b + (silicon content of molten iron - silicon content of molten iron of loading furnace) × c + (required pig iron mass - pig iron mass of loading furnace) × d + (required pig iron mass - molten iron mass of loading furnace) × e + scrap steel mass of loading furnace + (f - oxygen content of loading furnace end point) / 10 × b; The required molten iron mass is calculated by the following formula: Required molten iron mass = fixed converter loading mass - required scrap steel mass.

5. The scrap steel quality prediction method according to claim 1, characterized in that: The step of constructing an empirical model of scrap steel quality required by the steelmaking furnace based on the mechanism model using the target endpoint temperature, the molten iron composition, the molten iron temperature, and the influencing factor parameters includes: The calculation parameters, standard setting values ​​and affected tonnage corresponding to the steelmaking furnace are determined according to the target endpoint temperature, the molten iron composition, the molten iron temperature and the influencing factor parameters; wherein the calculation parameters include at least: target temperature, molten iron temperature, molten iron silicon percentage content, required pig iron quality, required molten iron quality, and furnace molten iron quality; the standard setting values ​​include at least: standard target temperature, standard molten iron temperature, standard molten iron silicon percentage content, standard pig iron quality, standard molten iron quality, standard scrap steel quality f, and standard endpoint oxygen content; the affected tonnage includes at least: the tonnage a of the impact of each 1 degree change in target temperature on the required scrap steel quality, the tonnage b of the impact of each 1 degree change in molten iron temperature on the required scrap steel quality, the tonnage c of the impact of each 1% change in molten iron silicon percentage content on the required scrap steel quality, the tonnage d of the impact of each 1 ton change in pig iron quality on the required scrap steel quality, and the tonnage e of the impact of each 1 ton change in molten iron quality on the required scrap steel quality; An empirical model of the scrap steel quality required for the steelmaking furnace is constructed based on the mechanism model and using the calculation parameters, the standard setting values, and the impact tonnage; wherein the empirical model is used to calculate the required scrap steel quality using the calculation parameters, the standard setting values, and the impact tonnage; wherein the required scrap steel quality is calculated using the following formula: Required scrap steel mass = (target temperature - standard target temperature) × a + (molten iron temperature - standard molten iron temperature) × b + (molten iron silicon percentage content - standard molten iron silicon percentage content) × c + (required pig iron mass - standard pig iron mass) × d + (required molten iron mass - standard molten iron mass) × e + standard scrap steel mass + (f - standard endpoint oxygen content) / 10 × b; wherein, the standard target temperature is 1650-1750°C, the standard molten iron temperature is 1200-1300°C, the standard molten iron silicon content percentage content is 0.3%-0.5%, the standard pig iron mass is 0.01-0.03 tons, the standard molten iron mass is 175-185 tons, the standard scrap steel mass is 25-40 tons, and the standard endpoint oxygen content is 450-550 ppm.

6. The method for predicting scrap steel quality according to claim 1, wherein: The step of constructing a production sample of the steelmaking furnace based on the empirical model, and performing prediction calculation on the production sample using a twin support vector regression machine and a whale swarm algorithm to obtain the required scrap steel quality of the steelmaking furnace in the next heat includes: Using the required scrap steel quality output by the empirical model and the corresponding production parameters thereof, the production sample corresponding to the steelmaking furnace is constructed; Constructing a scrap steel quality prediction model required for the next heat corresponding to the production sample according to the twin support vector regression machine, and calculating a temperature error value corresponding to the required scrap steel quality prediction model using the preset whale group algorithm; After predicting and calculating the production sample based on the temperature error value, the required scrap steel mass of the steelmaking furnace in the next heat is obtained.

7. A scrap steel quality prediction system, characterized in that: The system comprises: an initialization module for calculating the target endpoint temperature of the steelmaking furnace according to the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, and calculating the molten iron composition and molten iron temperature of the steelmaking furnace in the next heat; A mechanism model construction module, for constructing a mechanism model of the scrap steel quality required by the steelmaking furnace based on the material balance parameters and heat balance parameters of the steelmaking furnace; an influencing factor determination module, configured to determine a production process variable corresponding to the steelmaking furnace through the production parameters, and determine an influencing factor parameter of scrap steel required by the steelmaking furnace based on the influencing factors corresponding to the production process variables; an empirical model construction module, configured to construct an empirical model of the scrap steel quality required by the steelmaking furnace based on the target endpoint temperature, the molten iron composition, the molten iron temperature, and the influencing factor parameters and on the basis of the mechanism model; a scrap steel quality prediction module, configured to construct a production sample of the steelmaking furnace based on the empirical model, and to obtain the required scrap steel quality of the next heat of the steelmaking furnace after performing prediction calculations on the production sample using a twin support vector regression machine and a whale swarm algorithm; The initialization module is further used, in the process of calculating the target endpoint temperature of the steelmaking furnace according to the production parameters of the current heat of the steelmaking furnace and the production plan of the next heat, to: determine the temperature parameters corresponding to the steelmaking furnace according to the production parameters of the current heat of the steelmaking furnace, and determine the corrected temperature corresponding to the steelmaking furnace according to the production plan of the next heat; obtain the liquidus temperature included in the temperature parameters , superheat of molten steel in tundish , Temperature change from the end of refining to the start of pouring , Temperature changes during refining , Temperature change from steel tapping to refining , and obtain the correction temperature of the pouring order contained in the correction temperature , Corrected temperature of the steel ladle state , Corrected temperature for pouring time , Corrected temperature of steel tapping process ; Using the liquidus temperature , the superheat of the molten steel in the tundish , the temperature change from the completion of refining to the start of pouring , the changing temperature of the refining process , the temperature change from the completion of steel tapping to the refining , the corrected temperature of the pouring sequence , the corrected temperature of the steel ladle state , the corrected temperature of the pouring time , the corrected temperature of the steel tapping process Calculate the target endpoint temperature of the steelmaking furnace ; Wherein, the target endpoint temperature Calculated by the following formula: ; During the process of calculating the molten iron composition and molten iron temperature of the steelmaking furnace in the next heat, the initialization module is further used to: obtain the station parameters and sample parameters of the molten iron corresponding to the steelmaking furnace in the current heat, and determine the composition and temperature of the molten iron based on the station parameters and the sample parameters; determine the tank number and tank age corresponding to the molten iron tank in the steelmaking furnace, store the molten iron in the molten iron tank according to the tank number and the tank age based on the composition and the temperature, and obtain the molten iron composition table and molten iron temperature table corresponding to the molten iron tank; obtain the molten iron tank required for the steelmaking furnace in the next heat based on the production parameters, calculate the molten iron composition and the molten iron temperature according to the tank number and the tank age corresponding to the molten iron tank and based on the molten iron composition table and the molten iron temperature table.

8. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of the scrap steel quality prediction method according to any one of claims 1 to 6.

Images