Finish rolling inlet temperature forecast control method and device, electronic equipment and storage medium

Abstract

The invention provides a finish rolling inlet temperature forecast control method and device, electronic equipment and a storage medium, and relates to the technical field of steel rolling, and the method comprises the following steps: firstly, constructing a temperature forecast control model based on historical data in the hot rolling cooling process of different plates, and then according to the temperature data collected at the real temperature and the output result of the temperature forecast control model, calculating the temperature forecast control value; dynamically adjusting parameters of the temperature forecast control model; based on the deviation between the temperature distribution predicted by the temperature forecast control model and the target temperature distribution, parameters of a cooling system are adjusted so as to control the cooling temperature of a finish rolling inlet; through the method, the technical problem that the cooling temperature control precision is low in the hot rolling production process is solved, and the technical effects of improving the temperature stability of a finish rolling inlet, and improving the cooling efficiency and the product quality stability are achieved.

Description

Technical Field

[0001] The present application relates to the field of steel rolling technology, and in particular to a finishing rolling inlet temperature prediction and control method, device, electronic equipment and storage medium. Background Art

[0002] Hot rolling is a crucial process in the steel industry, transforming heated steel slabs into plates of defined shapes and sizes. During the hot rolling process, the finishing step has a decisive influence on the quality of the final product, and controlling the finishing inlet temperature is a key parameter for ensuring product quality and production stability.

[0003] Modern hot-rolling lines commonly use air-water atomization cooling systems to regulate the temperature of the steel strip at the finishing mill entrance. A typical air-water atomization cooling system currently consists of a fan, air duct, nozzle array, cooling water, and temperature sensors. The cooling air volume and velocity are controlled by adjusting the fan speed and damper opening. The nozzles mix cooling water with compressed air to form an atomized medium, which is sprayed onto the steel strip surface. The temperature sensor collects the steel strip surface temperature in real time and feeds this data back to the control system, enabling closed-loop regulation.

[0004] However, in actual production, due to factors such as changes in the running speed of the steel strip, the mechanical inertia of the cooling system, and ambient temperature fluctuations, the existing air-water atomization cooling system often has the problem of insufficient temperature control accuracy, which directly affects the rolling force distribution and product dimensional accuracy. In severe cases, it can lead to surface quality defects of the strip and abnormal rolling mill load. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a finishing rolling inlet temperature prediction control method, device, electronic equipment and storage medium to solve the technical problem of low cooling temperature control accuracy in the hot rolling production process in the prior art.

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting and controlling the finishing rolling inlet temperature, the method comprising: A temperature prediction and control model is constructed based on historical data from the hot rolling cooling process of different plates. The historical data includes the material, thickness, and temperature variation of the plates transferred from the rough rolling outlet to the finishing rolling entrance under corresponding cooling conditions. Dynamically adjust the parameters of the temperature prediction control model according to the real-time collected temperature data and the output result of the temperature prediction control model; Based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution, the parameters of the cooling system are adjusted to control the cooling temperature at the finishing rolling entrance.

[0007] In some optional implementations, the input parameters of the above-mentioned temperature prediction control model include: initial rolling outlet temperature, temperature learning coefficient, time difference, radiation ratio, specific heat and specific gravity; the output parameters of the above-mentioned temperature prediction control model include finishing rolling inlet temperature; the above-mentioned temperature prediction control model calculates the average value of the above-mentioned finishing rolling inlet temperature to predict the temperature distribution of each plate in the current cooling process.

[0008] In some optional implementations, the method for obtaining the input parameters of the above-mentioned temperature prediction control model includes: determining the initial rolling outlet temperature of the above-mentioned plate through data collected by an infrared pyrometer; determining the above-mentioned temperature learning coefficient based on the ambient temperature, plate temperature and stage coefficient of different cooling stages; determining the above-mentioned time difference through the first timestamp of the temperature collection point of the above-mentioned plate reaching the above-mentioned initial rolling outlet and the second timestamp of the temperature collection point reaching the above-mentioned finishing rolling entrance; determining the value of the radiation ratio corresponding to the above-mentioned plate in the current cooling stage by using a preset relationship model between the radiation ratio and the plate characteristics; determining the specific heat value corresponding to the above-mentioned plate in the current cooling stage according to the relationship curve between the specific heat and temperature determined in advance through experiments; and determining the specific gravity value of the above-mentioned plate according to the material of the above-mentioned plate.

[0009] In some optional implementations, the parameters of the temperature prediction control model are dynamically adjusted based on the real-time collected temperature data and the output results of the temperature prediction control model, including: comparing the predicted finishing rolling inlet temperature output by the temperature prediction control model with the actually measured finishing rolling inlet temperature, and calculating the temperature deviation between the two; dynamically correcting the temperature learning coefficient using a feedback control algorithm based on the size and change trend of the temperature deviation; when the temperature deviation exceeds a preset threshold, recalibrating at least one of the ambient temperature, radiation ratio, specific heat or time difference in the input parameters.

[0010] In some optional implementations, based on the deviation between the temperature distribution predicted by the above-mentioned temperature prediction control model and the target temperature distribution, the parameters of the cooling system are adjusted to control the cooling temperature at the finishing entrance, including: using the adjusted above-mentioned temperature prediction control model to predict the temperature distribution in the current cooling process; comparing the predicted results of the above-mentioned temperature distribution with the set target temperature distribution; and determining the parameter adjustment strategy of the cooling system according to the range of the comparison result exceeding the standard temperature deviation to control the cooling temperature at the finishing entrance.

[0011] In some optional implementations, the parameters of the cooling system include: cooling wind speed, cooling time and injection flow rate; determining the parameter adjustment strategy of the cooling system, including: constructing a three-dimensional geometric model of the cooling system according to the structure of the finishing entrance area; the cooling system includes a nozzle arranged on the transmission path of the plate, and the nozzle is used to spray air-water atomization to the plate; based on the target temperature of the current cooling stage and the preset cooling parameters, the cooling process of the plate is simulated using the three-dimensional geometric model; and optimizing the parameter adjustment strategy of the cooling system based on the simulation results.

[0012] In some optional implementations, the parameter adjustment strategy of the above-mentioned cooling system is optimized based on the simulation results, including: determining the impact of different nozzle layouts, injection speeds and injection angles on the cooling uniformity and cooling efficiency of the above-mentioned plate based on the above-mentioned simulation results; generating a cooling parameter adjustment strategy based on the impact analysis results, and the above-mentioned cooling parameter adjustment strategy includes: adjusting the distribution density and arrangement of the nozzles on the transmission path of the above-mentioned plate; adjusting the injection speed, injection angle and / or injection time of the above-mentioned nozzles.

[0013] In a second aspect, an embodiment of the present invention provides a finishing rolling inlet temperature prediction and control device, the device comprising: A model building unit is used to build a temperature prediction control model based on historical data of the hot rolling cooling process of different plates, wherein the historical data includes the material and thickness of the plates transferred from the rough rolling outlet to the finishing rolling entrance, as well as the temperature change data under the corresponding cooling conditions; A model optimization unit, configured to dynamically adjust the parameters of the temperature prediction control model based on the real-time collected temperature data and the output result of the temperature prediction control model; The temperature control unit is used to adjust the parameters of the cooling system to control the cooling temperature at the finishing rolling entrance based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0015] In a fourth aspect, an embodiment of the present invention 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 execute any method described in the first aspect above.

[0016] The present invention provides a method, device, electronic device and storage medium for temperature prediction control at the finishing rolling entrance. The method first constructs a temperature prediction control model based on historical data from the hot rolling cooling process of different plates. The historical data includes the material of the plates transmitted from the rough rolling exit to the finishing rolling entrance, the plate thickness and the temperature change data under the corresponding cooling conditions. Then, according to the real-time collected temperature data and the output results of the temperature prediction control model, the parameters of the temperature prediction control model are dynamically adjusted. Then, based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution, the parameters of the cooling system are adjusted to control the cooling temperature at the finishing rolling entrance. The above method solves the technical problem of low cooling temperature control accuracy in the hot rolling production process in the prior art, and achieves the technical effects of improving the temperature stability of the finishing rolling entrance, improving cooling efficiency and product quality stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of a method for predicting and controlling the finishing rolling inlet temperature provided by an embodiment of the present invention; Figure 2 A schematic structural diagram of a cooling system for hot-rolled plates provided in an embodiment of the present invention; Figure 3 A schematic structural diagram of a finishing rolling inlet temperature prediction and control device provided by an embodiment of the present invention; Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0021] It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures. Some embodiments of the present invention are described in detail below with reference to the accompanying figures. The following embodiments and features of the embodiments may be combined with each other unless there is a conflict.

[0022] During hot rolling production, controlling the air cooling temperature at the hot rolling mill inlet presents challenges such as temperature fluctuation, delayed response, and low cooling efficiency. While traditional PID control can regulate temperature to a certain extent, its accuracy is limited and it struggles to adapt to complex and changing production environments. Some technologies employ fuzzy control or digitalization, but these still face challenges such as poor environmental adaptability, high system complexity, and insufficient real-time data processing capabilities.

[0023] Based on this, this solution proposes a finishing rolling inlet temperature prediction control method, device, electronic equipment and storage medium to solve the technical problem of low cooling temperature control accuracy in the hot rolling production process in the existing technology.

[0024] To facilitate understanding of this embodiment, a method for predicting and controlling the finishing rolling inlet temperature disclosed in an embodiment of the present invention is first described in detail. Figure 1 The flow chart of a method for predicting and controlling the temperature at the finishing rolling inlet is shown in FIG. Figure 2 The cooling system of a hot-rolled plate shown in FIG. 1 mainly includes the following steps S110 to S130: S110: constructing a temperature prediction control model based on historical data of the hot rolling cooling process of different plates, the historical data including the material of the plates transferred from the rough rolling outlet to the finishing rolling entrance, the plate thickness, and the temperature change data under corresponding cooling conditions; The temperature prediction control model can be used to predict the temperature distribution of different types of plates during the cooling process. In this embodiment, the material of the plate generally refers to the main material of the hot-rolled plate, which can be low carbon steel, high strength alloy steel, silicon steel, heat resistant steel or high temperature alloy.

[0025] Cooling conditions refer to factors that affect the heat transfer rate and temperature distribution of the plate during the cooling process, which mainly include external environmental conditions (such as ambient temperature) and process parameters (such as parameters of the cooling system).

[0026] The temperature change data may refer to the different temperature values ​​corresponding to the change in the temperature of the plate surface over time or the corresponding cooling conditions. The temperature value may be acquired in real time under the corresponding cooling conditions by a temperature sensor (such as an infrared pyrometer or a thermocouple).

[0027] The above historical data may be temperature data collected from a long-term production process under different cooling conditions, so as to be used to establish a temperature prediction control model.

[0028] S120: Dynamically adjusting the parameters of the temperature prediction control model according to the real-time collected temperature data and the output result of the temperature prediction control model; The above-mentioned real-time collected temperature data may include the initial rolling outlet temperature and the finishing rolling inlet temperature, which can be collected by temperature sensors set at corresponding positions (initial rolling outlet and finishing rolling inlet).

[0029] As a specific example, the input parameters of the temperature prediction control model may include: the initial rolling exit temperature, the temperature learning coefficient, the time difference, the radiation ratio, the specific heat, and the specific gravity; and the output parameter of the temperature prediction control model may include the finishing rolling inlet temperature. In other words, the temperature prediction control model can calculate the average finishing rolling inlet temperature to predict the temperature distribution of each plate during the current cooling process.

[0030] In one embodiment, the dynamic adjustment of the parameters of the temperature prediction control model can be achieved in the following way: first, the predicted finishing rolling inlet temperature output by the temperature prediction control model is compared with the actually measured finishing rolling inlet temperature, and the temperature deviation between the two is calculated; then, according to the size and change trend of the temperature deviation, the temperature learning coefficient is dynamically corrected using a feedback control algorithm; when the temperature deviation exceeds a preset threshold, at least one of the ambient temperature, radiation ratio, specific heat or time difference in the input parameters is recalibrated to obtain a temperature prediction control model with updated parameters.

[0031] S130: Based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution, adjusting the parameters of the cooling system to control the cooling temperature at the finishing rolling entrance.

[0032] The target temperature distribution may refer to the specific temperature values ​​that each part of the plate is expected to reach at the entrance of the finishing rolling mill, and may usually be pre-set according to the production process requirements and product quality standards.

[0033] In one embodiment, the parameters of the cooling system include cooling air velocity, cooling time, and spray flow rate. The parameters of the cooling system can be used to modify the cooling rate and adjust the temperature distribution.

[0034] Furthermore, the implementation method of the above S130 may include: using the adjusted temperature prediction control model to predict the temperature distribution in the current cooling process; comparing the predicted result of the temperature distribution with the set target temperature distribution; and determining the parameter adjustment strategy of the cooling system based on the comparison result exceeding the range of the standard temperature deviation to control the cooling temperature at the finishing rolling entrance.

[0035] In one embodiment, the temperature prediction control model can be constructed based on a multivariate regression model or a machine learning model. Furthermore, the input parameters of the temperature prediction control model may include: the initial rolling exit temperature, the temperature learning coefficient, the time difference, the radiation ratio, the specific heat, and the specific gravity; and the output parameter of the temperature prediction control model may include the finishing rolling inlet temperature. In other words, the temperature prediction control model can calculate the average finishing rolling inlet temperature (i.e., the temperature learning effect) to predict the temperature distribution of each plate during the current cooling process.

[0036] As a specific example, the formula for calculating the average value of the finishing rolling inlet temperature is: (Formula 1); Among them, Fet Cal Indicates the average temperature of the finishing rolling entrance, in °C; Rdt Cal Indicates the average temperature of the initial rolling outlet, in °C; Ep Con Indicates radiation ratio; Sig Con represents the Stefan-Boltzmann constant in kcal / m 2 hr℃ 4 ; Tim(1) represents the time difference from the initial rolling exit to the finishing rolling entrance of the plate, in hr; Cp Con Indicates specific heat t, unit is kcal / kg℃; Gam Con Indicates specific gravity in kg / m 3 ;Lct Lay Represents the temperature learning coefficient; Rdh Mod Indicates the initial rolled outlet thickness in mm.

[0037] In this embodiment, the average value of the above-mentioned finishing rolling inlet temperature can be used to subsequently dynamically adjust the key control parameters of the hot-rolled plate during the cooling process at the finishing rolling inlet, so as to achieve accurate prediction of the temperature distribution and control of the cooling rate, thereby optimizing the cooling process and improving the overall performance and quality stability of the plate; at the same time, by calculating the average value of the temperature learning effect, the temperature change law during the cooling process can be quantified, providing a scientific basis for subsequent process adjustment and parameter optimization.

[0038] Furthermore, gradient descent or other optimization algorithms can be used to gradually optimize the temperature prediction control model based on the deviation between the real-time temperature data and the target temperature distribution. As a specific example, the temperature learning coefficient can be adjusted based on the error between the temperature distribution predicted by the model and the actual distribution. The value of , so that it meets the optimization conditions: (Formula 2); in, is the learning rate, and E is the prediction error.

[0039] After updating the parameters, the optimized temperature learning coefficient Substitute into the formula and recalculate the average value of the finishing rolling entrance temperature (i.e., temperature learning effect).

[0040] Furthermore, in some embodiments, the input parameters of the temperature prediction control model can be obtained in the following manner: (1) Determine the initial rolling outlet temperature of the plate through the data collected by the infrared pyrometer; The infrared pyrometer may be a non-contact infrared pyrometer installed at the initial rolling exit, and calculates the temperature value by collecting infrared light radiated from the surface of the plate at a temperature collection point.

[0041] To ensure uniform temperature distribution across the entire plate, several key points (or key areas) on the plate can be selected as temperature collection points (or temperature collection areas). For example, the temperature at the plate's geometric center can be collected; or a point at the plate's head can be selected to collect the temperature just after it leaves the primary rolling mill exit; or a point at the plate's tail can be selected to collect the temperature just after it leaves the primary rolling mill exit.

[0042] In some other examples, multiple key points can be selected on the plate as temperature collection points. By detecting the temperature of these key points, the temperature distribution of the plate can be more comprehensively understood, so that corresponding control measures can be taken to ensure the stability of the production process and product quality.

[0043] (2) Determine the temperature learning coefficient based on the ambient temperature, plate temperature and stage coefficient at different cooling stages; During the hot rolling cooling process, the plate typically undergoes different cooling stages from the initial rolling exit to the final rolling entrance. The heat transfer environment and cooling rate may vary significantly during these stages. To achieve more accurate prediction results, in some embodiments, the temperature learning coefficient can be adjusted based on the different cooling stages.

[0044] As a specific example, the cooling phase can be divided into an initial rapid cooling phase, an intermediate stable cooling phase, and a final slow cooling phase. The temperature learning coefficient can be dynamically adjusted based on the current cooling phase and heat transfer environment. Furthermore, in the initial rapid cooling phase, due to the large temperature gradient and high heat transfer rate, the temperature learning coefficient should be large to reflect the rapid temperature change. In the intermediate stable cooling phase, due to the gradual decrease in temperature gradient and the corresponding decrease in heat transfer rate, the temperature learning coefficient should be appropriately reduced. In the final slow cooling phase, due to the very small temperature gradient and low heat transfer rate, the temperature learning coefficient should be further reduced.

[0045] For example, the temperature learning coefficient for the initial rapid cooling phase is alpha = alpha0 + k1 × (Tsteel - Tenv), the temperature learning coefficient for the intermediate stable cooling phase is alpha = alpha0 + k2 × (Tsteel - Tenv), and the temperature learning coefficient for the final slow cooling phase is alpha = alpha0 + k3 × (Tsteel - Tenv). Tsteel is the current plate temperature, and Tenv is the current ambient temperature. The basic learning coefficient alpha0 is 0.5, the initial phase proportionality constant k1 is 0.1, the stable phase proportionality constant k2 is 0.05, and the final phase proportionality constant k3 is 0.01. In practical applications, these parameters can be verified and adjusted using experimental data to ensure that the temperature learning coefficients accurately reflect the heat transfer environment at different cooling stages.

[0046] In this embodiment, by dynamically adjusting the temperature learning coefficient, the control system for executing the finishing rolling inlet temperature prediction control method provided by the embodiment of the present invention can flexibly adjust parameters according to the characteristics of the actual plate.

[0047] As a specific example, the temperature learning coefficient Lct Lay Dynamic adjustment can be achieved in the following ways: First, by collecting the surface temperature and internal temperature of the plate during the cooling process in real time, combined with historical data (including cooling laws under different materials, thicknesses and process conditions), a data-driven temperature learning coefficient model is established.

[0048] Then, the temperature learning coefficient model is used to fit and predict the deviation between the real-time temperature change and the target temperature; the key influencing factors in the cooling process (such as initial temperature, time difference, plate thickness and cooling wind speed, etc.) are extracted, and the weight parameters of the temperature learning coefficient model are dynamically updated. Then, based on the prediction results of the temperature learning model, the temperature learning coefficient Lct is calculated. Lay The value of is adjusted to the optimal value suitable for the current cooling environment.

[0049] (3) Determine the time difference between the first time stamp when the plate temperature collection point reaches the preliminary rolling exit and the second time stamp when the plate temperature reaches the finishing rolling entrance; Among them, the above-mentioned first timestamp can be the first moment recorded by the synchronous clock system when the temperature collection point of the plate reaches the initial rolling exit; the second timestamp can be the second moment recorded by the synchronous clock system when the temperature collection point of the plate reaches the finishing rolling entrance, and the time difference is the difference between the second moment and the first moment.

[0050] As a specific example, the method of determining the time difference may include: collecting the temperature data of the plate (temperature collection point) at the initial rolling exit through a non-contact infrared pyrometer installed at the initial rolling exit (the precise temperature value is calculated after the infrared light radiated from the surface of the plate is converted into an electrical signal), and recording the time point t1 when it passes the initial rolling exit; detecting the surface temperature distribution and real-time changes of the plate through a non-contact infrared pyrometer set at the finishing rolling entrance, and detecting the position change of the plate (temperature collection point) when it arrives at the finishing rolling entrance through a position sensor, and recording the arrival time t2; and the time difference .

[0051] (4) Using the preset relationship model between the radiation ratio and the plate characteristics, determine the radiation ratio value corresponding to the plate in the current cooling stage; The emissivity ratio, defined as the ratio of an object's ability to emit thermal radiation to that of an ideal blackbody, is commonly used in thermal radiation calculations. In this solution, the emissivity ratio is used to calculate the amount of heat transferred by radiation from hot-rolled plates during cooling. Using the Stefan-Boltzmann law, the emissivity ratio is a key parameter in estimating the heat loss from radiation during cooling.

[0052] Radiation heat transfer is one of the primary ways that plates dissipate heat under high-temperature conditions. Therefore, accurately determining the radiation ratio is crucial for accurate temperature prediction. Different materials (such as different steel grades) have different radiation ratios. Determining the precise radiation ratio through experimentation can improve the accuracy of heat loss calculations during cooling, thereby enhancing the precision of finishing inlet temperature predictions.

[0053] Among them, the method for obtaining the relationship model between the radiation ratio and the plate properties may include: obtaining the radiation ratio data of multiple plate samples under different temperatures and surface conditions through repeated experiments, and then performing regression analysis on the experimental results to fit the relationship model between the radiation ratio and the plate properties.

[0054] Furthermore, the fitted radiation ratio formula or table lookup method is used in the above-mentioned relationship model between the radiation ratio and the plate properties, and the applicable radiation ratio value is selected according to the material and cooling conditions of the plate, so as to determine the radiation ratio value corresponding to the pre-cooling stage.

[0055] In some embodiments, the above-mentioned experiment of obtaining radiation ratio data can be implemented by performing the following process through a radiation ratio experimental device. Specifically, the radiation ratio experimental device may include: a radiation heat flux measuring device (composed of a high-precision heat flux meter and an infrared radiation thermometer, which are used to measure the heat flux density q radiated from the plate surface and the real-time temperature T of the plate surface, respectively). S ), temperature controlled experimental furnace (used to simulate the cooling environment of hot rolled plates and adjust the ambient temperature T e and radiation intensity), plate samples (a variety of materials including but not limited to low carbon steel, high strength alloy steel, silicon steel, heat resistant steel and high temperature alloy, and samples with untreated original hot-rolled surfaces and thick surface oxide layers) are selected. In this embodiment, the materials of the plate samples are low carbon steel and high strength alloy steel, and the thickness range is: 2 mm, 4 mm, and 6 mm.

[0056] As a specific example, the process of the radiation ratio experiment includes: Step 1. Sample preparation: Clean the surface of the plate sample and record its material, thickness, surface roughness and color characteristics; Step 2: Experimental setup: Place the sample in the experimental furnace and heat it to a target temperature close to the actual blooming exit temperature; Step 3: Measure heat flux and temperature: Use an infrared radiation thermometer (or high-precision infrared thermometer) to detect the sample surface temperature in real time; use a heat flux meter to measure the heat flux density radiating outward from the sample surface; Step 4: Calculate the radiation ratio: Calculate the radiation ratio according to the Stefan-Boltzmann law. The calculation formula is: (Formula 3); Where q represents the heat flux density radiated from the sample surface (unit: W / m 2 );Sig Con represents the Stefan-Boltzmann constant ( );T S Indicates the sample surface temperature (unit: K); T e Indicates the ambient temperature (unit: K).

[0057] Step 5: Data processing: Repeat the experiment to obtain radiation ratio data of multiple samples under different temperatures and surface conditions; perform regression analysis on the experimental results to fit a relationship model between radiation ratio and sample characteristics; Step 6. Application of results: Use the fitted radiation ratio formula or table lookup method in the model to select the appropriate radiation ratio value based on the plate material and cooling conditions.

[0058] Furthermore, the radiation ratio Ep can be changed experimentally ConThe value of is studied to study its effect on the cooling performance of the plate (including cooling rate and temperature distribution uniformity) to determine the radiation ratio value that can achieve the best cooling effect. In one embodiment, the experimental method and data analysis for determining the optimal radiation ratio may include the following steps: <1> Experimental equipment includes: 1. High-precision heat flow meter, used to measure the heat flux density q radiated from the plate surface; 2. Infrared radiation thermometer, used to measure the real-time temperature T of the plate surface s ; 3. Temperature controlled experimental furnace, used to simulate hot rolling environment and adjust the ambient temperature T e and radiation intensity; The materials of the plate samples are low carbon steel and high strength alloy steel; the thickness range of the plate samples is: 2 mm, 4 mm, and 6 mm.

[0059] <2>, the experimental steps are as follows: 1. Sample preparation: Surface treatment (polishing, spraying oxide layer, etc.) of the plate sample to change its radiation ratio; use samples with different surface conditions (radiation ratio range Ep Con =0.3~1.1).

[0060] 2. Experimental setup: Heat the sample to 900-1200°C; set the ambient temperature T e =50°C; control the sample surface radiation ratio Ep Con , record the corresponding cooling rate and final temperature distribution.

[0061] 3. Data collection: Real-time recording of sample surface temperature T s (t), ambient temperature T e , and radiation heat flux density q.

[0062] 4. Data processing: Use the Stefan-Boltzmann formula to calculate the heat transfer efficiency under different radiation ratios: (Formula 4); Where q is the heat flux density of radiation heat transfer (i.e. the heat flux density of radiation from the sample surface), which represents the amount of heat radiation transferred per unit area (W / m 2 );Ep Con is the sample surface radiation coefficient (i.e. radiation ratio); Sig Con is the Stefan-Boltzmann constant ( );T s is the sample surface temperature (K); T e is the ambient temperature (K).

[0063] The experimental results are shown in Table 1 below: Table 1 - Radiation ratio experimental results;

[0064] <3>、Analysis of experimental results: 1. Relationship between cooling rate and radiation ratio: radiation ratio Ep Con When the heat flux q increases, the cooling rate R c Then it increases. Con When the value is greater than 0.7, the cooling rate tends to increase slowly.

[0065] 2. Temperature distribution uniformity: When the radiation ratio is 0.7, the temperature uniformity is the best (deviation Minimum). The radiation ratio is too large (such as Ep Con =1.1), the surface supercooling phenomenon increases, resulting in a larger temperature difference between the interior and the surface.

[0066] 3. Determination of the optimal radiation ratio: Taking into account the cooling rate and temperature uniformity, the optimal radiation ratio is 0.9.

[0067] Furthermore, the specific heat and specific gravity in the input parameters of the above-mentioned temperature prediction control model can be determined experimentally and used to accurately calculate the energy transfer and temperature changes of the hot-rolled plate during the cooling process at the finishing rolling entrance, so as to improve the control accuracy of the cooling process; the specific heat and specific gravity parameters determined experimentally can provide reliable data support for the calculation of the average value of the temperature learning effect, thereby optimizing the heat transfer model in the cooling process, improving the cooling efficiency, and ensuring the uniformity of the plate temperature distribution and the consistency of product performance.

[0068] (5) Determine the specific heat value of the plate at the current cooling stage based on the relationship curve between specific heat and temperature determined in advance through experiments; Specific heat refers to the amount of heat a material absorbs per unit mass to increase its temperature per unit. It is generally expressed in kcal / (kg·°C). As an inherent thermophysical property of a material, specific heat can be used to characterize its response to temperature changes. During the cooling process, specific heat determines how much heat a sheet absorbs or releases during temperature changes.

[0069] In this solution, specific heat is used to calculate the heat released by the plate during cooling. This, along with temperature change and mass, determines the change in energy during cooling and is a crucial parameter for calculating the temperature change during cooling. Experimentally determining the specific heat values ​​of different materials allows the model to better fit actual operating conditions and improve the reliability of temperature predictions.

[0070] In one example, an experimental method for determining specific heat values ​​may include testing the main material of a hot-rolled plate (e.g., low-carbon steel or high-strength alloy steel) using a differential scanning calorimeter (DSC). A standard-sized sample is placed in a temperature-controlled environment and gradually heated from room temperature to a target temperature. The amount of heat absorbed by the sample, its mass, and temperature change are recorded, and the specific heat value is calculated according to the following formula: (Formula 5); Where Q represents the absorbed heat (J), m represents the sample mass (kg), and △t represents the temperature difference; The relationship curve between specific heat and temperature is generated based on the experimental results, providing accurate thermophysical property parameter support for the calculation of temperature learning effect in the model.

[0071] In one embodiment, the specific method of experimentally measuring specific heat and data analysis may include the following steps: <1> The experimental method is differential scanning calorimetry (DSC); the experimental apparatus includes: 1. Differential Scanning Calorimeter (DSC): used to measure the relationship between the amount of heat absorbed or released by a sample and the change in temperature.

[0072] 2. Temperature control environment: The temperature control accuracy is ±0.1℃, and the test temperature range is 25~1000℃.

[0073] 3. Standard reference materials: Use materials with standard specific heat values ​​(such as aluminum oxide) to calibrate the instrument.

[0074] <2> Experimental steps: 1. Sample preparation: Take a standard sample of low-carbon steel or high-strength alloy steel with a mass of 0.5g; clean the sample surface to ensure there is no impurities or oxide scale.

[0075] 2. Experimental setup: Place the sample and reference material on the sample and reference pans of the DSC instrument, respectively. Set the heating rate to 10 K / min and the target temperature range to 25–900 °C.

[0076] 3. Data collection: Record the heat Q absorbed by the sample at different temperatures, the corresponding temperature change ΔT, and the sample mass m.

[0077] 4. Specific heat calculation formula: (Formula 5); Among them, Cp Con is the specific heat (unit: J / kg•℃); Q is the heat absorbed by the sample (unit: J); m is the mass of the sample (unit: kg); △t is the temperature change (unit: ℃). The experimental data are shown in Table 2 below: Table 2 - Experimental test results of specific heat;

[0078] Analysis of Experimental Results: The specific heat value of low-carbon steel increases with increasing temperature, rising from 2000 J / kg•°C to 3200 J / kg•°C within the 25-400°C range. The specific heat value of high-strength alloy steel follows a similar trend, but with a slightly higher absolute value.

[0079] (6) Determine the specific gravity of the board according to the material of the board.

[0080] Specific gravity refers to the mass of a substance per unit volume, and its unit is kg / m 3 As one of the fundamental physical properties of a material, specific gravity determines its heat capacity per unit volume. In this solution, specific gravity is used to calculate the mass of the plate per unit volume, which in turn is used to calculate energy change. Combined with parameters such as specific heat and thickness, specific gravity determines the overall heat capacity of the plate. The greater the mass of the material, the more heat it contains during cooling, resulting in a slower cooling rate. Specific gravity plays a role in calculating the overall thermal energy change and is a key factor influencing the rate of temperature change.

[0081] Different types of hot-rolled plates (e.g., different steel grades) may have different specific gravities. Experimental determination of the specific gravities can improve the accuracy of energy transfer calculations in the model and further enhance the model's adaptability to different materials.

[0082] As a specific example, the method of experimentally determining the specific gravity values ​​corresponding to different plate materials may include: testing the main material of the hot-rolled plate (such as low carbon steel or high-strength alloy steel) by the Archimedean method, measuring the sample mass m by a high-precision electronic scale, and then completely immersing the sample in a liquid of known density (such as water) to measure the volume V of the liquid displaced; calculating the specific gravity value based on the ratio of the sample mass m to the displaced liquid volume V, and taking the average value of multiple groups of sample tests as the specific gravity value corresponding to the plate material of the current sample.

[0083] In one embodiment, the specific method of experimentally measuring specific gravity and data analysis may include the following steps: <1> The experimental method is the Archimedean method; the experimental equipment includes: Electronic balance (accuracy 0.001g); known density liquid, choose pure water (density 1000kg / m 3 ); Experimental fixture, used to fix the sample to prevent it from moving during measurement.

[0084] <2> Experimental steps: 1. Sample preparation: Select a low-carbon steel or high-strength alloy steel sample with a mass of 5g; clean the sample surface to ensure there is no attachment.

[0085] 2. Experimental setup: measuring the mass m of the sample in air dry ; Immerse the sample completely in pure water and measure the buoyancy mass m after the water is removed buoyancy .

[0086] 3. Specific gravity calculation formula: Sample volume V sample , as shown below: (Formula 6); proportion , as shown below: (Formula 7); The experimental data are shown in Table 3 below: Table 3 - Experimental test results of specific gravity;

[0087] <3>, Experimental results analysis: The specific gravity of low carbon steel is about 7850kg / m 3 ; The specific gravity of high-strength alloy steel is slightly higher, about 8900kg / m 3 .

[0088] The above experimental results can provide accurate density parameter support for the calculation of temperature learning effect, so as to ensure the reliability and accuracy of model calculation.

[0089] Taking the experimental test results in the above embodiment as an example, the process of calculating the average value of the finishing rolling inlet temperature in combination with the model parameters obtained in real time may include the following steps: Real-time acquisition of model parameters, including: average temperature Rdt at the initial rolling outlet Cal , real-time detection is 1127°C; radiation ratio Ep Con , experimentally determined to be 0.35; the Stefan-Boltzmann constant Sig Con , ; Time difference from the initial rolling exit to the finishing rolling entrance Tim(1), 0.004hr; Specific heat Cp Con : Experimental determination: 0.9kcal / kg∙℃; specific gravity Gam Con : Experimental determination is 8850kg / m 3 ; Temperature learning coefficient Lct Lay , the initial value is 1.0, which is optimized to 1.02 after dynamic adjustment; the initial rolling outlet thickness Rdh Mod , real-time monitoring is 0.065m.

[0090] Substituting the above parameters into the formula for the average value of the finishing inlet temperature (i.e., Formula 1) for calculation, we can obtain: .

[0091] This scheme experimentally measures physical parameters such as radiation ratio, specific heat, and specific gravity, avoiding the errors caused by relying on empirical values ​​or fixed values, thereby improving the prediction accuracy and control stability of the temperature prediction control model.

[0092] In another embodiment, the above S120 dynamically adjusts the parameters of the temperature prediction control model based on the real-time collected temperature data and the output result of the temperature prediction control model, which may include: (S121) Compare the predicted finishing rolling inlet temperature output by the temperature prediction control model with the actually measured finishing rolling inlet temperature, and calculate the temperature deviation between the two; (S122) Dynamically correct the temperature learning coefficient using a feedback control algorithm based on the size and change trend of the temperature deviation; (S123) When the temperature deviation exceeds a preset threshold, recalibrate at least one of the input parameters, namely, the ambient temperature, the radiation ratio, the specific heat, or the time difference.

[0093] Through the above-mentioned dynamic correction of model parameters, the error between the predicted value and the measured value can be effectively reduced, and the prediction accuracy of the model can be significantly improved; the feedback control algorithm is used to dynamically correct the temperature learning coefficient, so that the model can self-adjust according to the changing trend of temperature deviation, thereby enhancing the adaptability and robustness of the model under different working conditions, and is suitable for continuous production processes under different plate materials and different environmental conditions; through recalibration of input parameters, model failure due to input parameter drift or measurement error can be prevented, thereby improving fault tolerance and stability.

[0094] (S124) Based on the historical deviation data generated by the plurality of plates during the cooling process, the model parameters are updated by online adaptive optimization using the least squares method or the Kalman filter method; this step enables the model to have continuous learning and optimization capabilities and adapt to parameter drift and process changes in long-term operation.

[0095] (S125) After the model parameters are updated, the predicted value of the finishing rolling inlet temperature is recalculated and stored in the control system for subsequent plate temperature prediction and cooling control. This step forms a closed-loop optimization control process, achieving complete closed-loop management from data acquisition, model prediction, deviation analysis, parameter update, to control execution.

[0096] Based on this, this embodiment constructs a temperature prediction control model with high precision, adaptability and continuous learning capabilities by introducing a dynamic feedback mechanism, an exception handling mechanism and an online parameter optimization mechanism. This model can achieve more precise temperature control, help improve the cooling uniformity and structural properties of the plate, reduce quality defects caused by poor temperature control, and improve the stability and efficiency of the production process.

[0097] In one embodiment, the parameters of the cooling system may include: cooling wind speed, cooling time, and injection flow rate; further, determining the parameter adjustment strategy of the cooling system may include: (S131) ​​constructing a three-dimensional geometric model of the cooling system according to the structure of the finishing rolling entrance area; Among them, the finishing rolling entrance area can include a cooling system and a finishing rolling stand F1, combined with Figure 2 As shown, the cooling system may include: a nozzle 210 , a guide 220 , a roller 230 , a control module 240 and a temperature sensor 250 .

[0098] The nozzle 210 is set at the exit of the plate from the initial rolling ( Figure 2 A) is transferred to the finishing entrance ( Figure 2 The nozzles (B) can be located above, below, or to the side of the sheet material along the transmission path. They spray air-water atomization (a mixture of compressed air and cooling water) onto the sheet material to remove impurities from the surface and cool it. The nozzle's position, spray angle, spray pressure, and spray area coverage all influence the cooling system's parameters, and thus the sheet material's surface temperature.

[0099] Guides 220 can be installed at the finishing mill entrance, on either side of, or above or below, the plate's path. They guide the plate accurately into the gap between rollers 230, preventing deviation and supporting the plate's stable operation before entering the finishing mill entrance. Rollers 230 can be installed on the finishing mill stand F1, serving as the core actuator for the first pass of finishing milling. Typically, the rollers, upper and lower, form the rolling gap through which the plate passes.

[0100] The control module 240 is connected to the nozzle 210 (electrically or communicatively) and is used to control the output of the nozzle 210, for example: controlling the number of nozzles 210 opened (to adjust the distribution density and arrangement of the nozzles on the transmission path of the plate); adjusting the nozzle's spray speed, spray angle and / or spray time, etc.

[0101] The temperature sensor 250 can be respectively set at the initial rolling outlet A and the finishing rolling entrance B to collect the temperature of the plate at the initial rolling outlet and the finishing rolling entrance in real time. In addition, the temperature sensor 250 can also be used to collect the temperature of the surrounding environment.

[0102] Furthermore, the temperature sensor 250 can be connected to the control module 240 (electrically connected or communicatively connected) to transmit the collected temperature signal to the control module 240. The control module 240 can dynamically adjust the parameters of the cooling system (such as: the layout of the nozzle 210, the injection speed, the injection angle, etc.) according to the target temperature and preset cooling parameters to achieve closed-loop control of the cooling process, thereby improving cooling uniformity and process stability.

[0103] (S132) Based on the target temperature of the current cooling stage and the preset cooling parameters, the cooling process of the plate is simulated using a three-dimensional geometric model; and a parameter adjustment strategy of the cooling system is optimized based on the simulation results.

[0104] In one embodiment, optimizing a parameter adjustment strategy for a cooling system based on simulation results may include: determining, based on the simulation results, the impact of different nozzle layouts, jet velocity, and jet angle on the cooling uniformity and efficiency of the plate; and generating a cooling parameter adjustment strategy based on the impact analysis results. The cooling parameter adjustment strategy may include adjusting the density and arrangement of nozzles along the plate's transport path; and adjusting the nozzle's jet velocity, jet angle, and / or jet time to control the cooling velocity and cooling time to match the heat transfer requirements of the current cooling stage.

[0105] Furthermore, in some examples, the cooling parameter adjustment strategy may further include: adjusting the spray angle of the nozzle to increase the coverage of the cooling medium on the surface of the plate.

[0106] Furthermore, the parameter adjustment strategy can be fed back to the control module of the cooling system to achieve closed-loop optimization control of the cooling parameters.

[0107] In this embodiment, by combining Computational Fluid Dynamics (CFD) technology, the air cooling process of hot-rolled plates in the finishing rolling entrance area is jointly modeled and simulated for fluid flow and heat conduction, so as to improve the simulation accuracy and control capability of the cooling process.

[0108] As a specific example, the above method may include the following steps: (S141) Establishing a three-dimensional geometric model of the cooling zone: Based on the actual structure of the finishing rolling entrance area, a refined three-dimensional model including components such as the plate, nozzle, guide, and roller is constructed.

[0109] (S142) Setting boundary conditions and moving walls: Set the plate as a moving wall, considering the disturbance of its movement on the airflow field; set the air inlet velocity, temperature, and turbulence parameters, use pressure boundary conditions at the outlet, and set heat conduction and convection boundaries on the wall.

[0110] (S143) Select appropriate turbulence and radiation models: such as the k-ε or k-ω turbulence model to simulate the flow characteristics of the spray air, and at the same time select an appropriate radiation model (P1, DO, etc.) to perform coupled calculations on the radiation heat transfer of the high-temperature surface of the plate.

[0111] (S144) Coupled convection and heat conduction mechanisms: The local heat transfer coefficient is automatically calculated through the convection heat exchange module of the CFD simulation software, and the internal heat conduction process of the plate is solved at the same time, realizing the synchronous evolution of the temperature field inside and outside the plate.

[0112] (S145) Nozzle layout and cooling parameter optimization: Use simulation models to simulate and compare multiple scenarios of nozzle layout, wind speed, spray angle and other parameters to evaluate the uniformity and efficiency of the cooling effect and optimize the cooling system design.

[0113] (S146) Build an offline prediction model and support closed-loop control: Based on a large number of CFD simulation results, a response surface model, surrogate model, or neural network model is constructed to quickly predict the relationship between cooling parameters and temperature evolution. In actual production, parameters such as rolling speed, plate thickness, and initial temperature are combined to achieve closed-loop regulation and control of the cooling process.

[0114] Through the above implementation, the prediction accuracy, adaptability and intelligence level of the cooling system can be significantly improved, which is particularly suitable for product scenarios such as hot-rolled high-strength steel and silicon steel that have high requirements for cooling uniformity and temperature control.

[0115] As a specific example, in order to achieve accurate simulation of the plate cooling process, it is necessary to first build a three-dimensional geometric model including the plate, cooling system and environment, and set the simulation conditions for multi-physics field coupling. Preferably, the geometric modeling can be done using CAD software (such as SolidWorks, ANSYS DesignModeler) to create a plate (size L×W×H, where L is the length, W is the width, H is thickness), nozzle array (candidate layout includes N The nozzles have coordinates ( x i , y i , z i ), i =1,2,…, N ) and transmission path (speed is vtrans ) three-dimensional geometric model.

[0116] Sheet material properties: density ρ s (kg / m 3 ), specific heat capacity c p,s (J / (kg·K)), thermal conductivity ks (W / (m·K)), which can be obtained from the material manual or differential scanning calorimetry (DSC) experiment.

[0117] Cooling medium properties: density of air (or water) ρ f (kg / m 3 ), dynamic viscosity μ (Pa·s), thermal conductivity k f (W / (m·K)), constant pressure specific heat capacity c p,f (J / (kg·K)), the ambient temperature T can be measured by the temperature sensor ∞ Then look up the table to obtain it.

[0118] Boundary condition settings: Initial condition: The initial temperature of the plate is T0 (℃), measured by an infrared thermal imager; Surface condition: The upper surface of the plate is the jet cooling boundary, and convective heat transfer and radiation heat transfer loads are applied; The lower surface and the environment are naturally convective heat transfer (the surface heat transfer coefficient hnat is 5-10 W / (m 2 ·K)); Nozzle outlet condition: spray medium temperature T j (℃, set by temperature control system), speed v j (m / s, variable to be optimized).

[0119] The simulation tool can use computational fluid dynamics (CFD) software (such as ANSYS Fluent, COMSOL Multiphysics) to perform multi-physics field coupling simulation. The solver can be set to a pressure-based transient solver, the turbulence model can use the Realizable k-ε model (suitable for high Reynolds number flow), and the radiation model can use the DO model (considering the influence of thermal radiation on the cooling process).

[0120] By simulating different cooling parameter combinations, we can quantitatively analyze the influence of nozzle layout, jet speed and jet angle on the cooling uniformity and cooling efficiency of the plate. For example: (1) Cooling uniformity evaluation index: Cooling uniformity is measured by the standard deviation σT of the plate surface temperature distribution, which is calculated as follows: (Formula 8); Where: T(x,y) is the temperature at position (x,y) on the plate surface (°C); is the average surface temperature (°C); A=L×W is the upper surface area of ​​the plate (m 2 ). The smaller σT is, the more uniform the temperature distribution is.

[0121] (2) Cooling efficiency evaluation index: The cooling efficiency η is defined as the ratio of the actual heat transfer Qactual to the ideal heat transfer Qideal, and the calculation formula is: (Formula 9); Where: Actual heat transfer Q actual It can be obtained by integrating the heat flux in the simulation: ; Ideal heat transfer Q ideal The plate is cooled from the initial temperature T0 to the ambient temperature T ∞ Theoretical maximum heat transfer: ; h eff is the effective convection heat transfer coefficient (W / (m 2 K), calculated from the Nusselt number (Nu) in the simulation: ; ε is the surface emissivity of the plate (dimensionless), which can be obtained by spectrometer measurement; σ = Stefan-Boltzmann constant; A s is the surface area of ​​the plate in contact with the cooling medium (m 2 ); V = L × W × H is the volume of the plate (m 3 ).

[0122] The larger η is, the higher the cooling efficiency is.

[0123] Furthermore, based on the simulation results, cooling parameters and evaluation indicators can be established through optimization algorithms (such as genetic algorithms and particle swarm optimization) ( σT 、 η ) to generate the optimal parameter adjustment strategy. A preferred method is: (1) Nozzle layout optimization; Optimization variables may include: nozzle distribution density ρ d (pieces / m 2 ) and arrangement methods (such as rectangular array, circular array, gradient array).

[0124] Since the distribution density ρ d If the value is too small, there will be uncovered areas on the surface of the plate, resulting in excessively high local temperatures; d When the value is too large, the mutual interference between nozzles increases, and energy utilization decreases. In addition, the gradient array (higher density in the center than at the edge) can compensate for the insufficient cooling caused by the weakened convective heat transfer at the edge of the plate (simulation shows that the temperature difference between the center and the edge can be reduced by 15%-20%).

[0125] Based on this, the optimization method may include: taking σT minimization as the goal, searching for the optimal ρ through genetic algorithm dAnd arrangement, the fitness function is defined as: (Formula 10); Where: ω1, ω2 are weight coefficients (ω1+ω2=1); C nozzle The cost of a single nozzle (yuan / piece) can be used to balance uniformity and economy.

[0126] (2) Optimization of jet speed and angle; Optimization variables include: jet wind speed v j (m / s), spray angle α (°, the angle with the normal line of the plate surface).

[0127] Due to the wind speed v j When the convective heat transfer coefficient h increases, eff Improve (h eff ∝v j 0.8 ), the cooling rate is faster, but the energy consumption (fan power ) increases significantly; when the angle α is 45°, the projected area of ​​the cooling medium on the plate surface is the largest (coverage C cover =cosα+sinα, when α=45°C cover =1.414), while reducing rebound losses (simulation shows that α = 45° increases the surface coverage by 20% compared to vertical injection (α = 90°).

[0128] Based on this, the optimization method may include: taking σT minimization and η maximization as multiple objectives, determining the optimal (v j ,α) combination, the specific formula is: (Formula 11); (3) Injection time adjustment; Optimization variable: single-stage injection time t c (s).

[0129] Due to the excessively long t c It will cause the plate to be too cold (temperature is lower than the target value), and too short t c The heat cannot be dissipated sufficiently.

[0130] Therefore, the optimization basis can be based on the heat conduction demand matching model to calculate the target temperature T target Minimum t of (t) c : (Formula 12); Where: q req (t) is the target heat flux (W / m 2 ), which means satisfying T target (t ) The instantaneous heat exchange between the cooling medium and the plate required; ρ s is the density of the board (unit: kg / m 3 ); δ ( t ) is the dynamic thermal penetration depth (m), which is used to indicate the effective depth affected by temperature changes. Its initial value is ( is the thermal diffusivity of the plate, t 0 is the initial cooling time), the final form is ( kδ is the adjustment coefficient, τ is the time constant, all calibrated through simulation or experiment); is the rate of change of target temperature over time (unit: K / s), which can be obtained from the target temperature curve T target ( t ) is derived (determined through process planning or experimental measurement).

[0131] Next, the optimized cooling parameters (nozzle layout, v j 、 α 、 t c ) is transmitted to the PLC (Programmable Logic Controller) of the cooling system via industrial Ethernet (such as PROFINET), and the nozzle drive mechanism (such as stepper motor to control the nozzle angle), the frequency converter (to adjust the fan speed to change the v j ) and solenoid valve (control injection time t c At the same time, the surface temperature of the plate is monitored in real time through an infrared thermal imager, forming a closed-loop control of "simulation optimization-parameter adjustment-real-time monitoring-re-optimization" to ensure that the cooling process is always in the optimal state.

[0132] This embodiment achieves precise adjustment of cooling parameters through three-dimensional simulation and multi-objective optimization, solves the problem of balancing uniformity and efficiency in traditional empirical adjustment, and provides technical support for the intelligent control of the plate cooling process.

[0133] Furthermore, in order to improve the temperature prediction accuracy of the model during the steel structure transformation stage, the embodiment of the present invention can also introduce the phase change thermodynamic mechanism, incorporate the phase change latent heat generated by the plate during the cooling process into the energy balance calculation of the temperature evolution process, and realize the dynamic response and coupling of the phase change behavior of different plate types and different cooling rates.

[0134] As a specific example, the specific implementation steps of the above method are as follows: (S151) Modeling of latent heat of phase transformation: For a specific steel grade, the latent heat value during the phase transformation from austenite to ferrite, bainite, pearlite, or martensite is obtained through thermodynamic databases, literature, or experimental methods (differential scanning calorimetry (DSC)). Combined with kinetic equations such as the JMAK model, the time-varying phase transformation fraction is calculated. Based on this, the latent heat released or absorbed per unit time is calculated and used as the heat source term in the energy equation to solve the temperature field.

[0135] (S152) Phase Transformation Kinetic Model Integration: Integrating the material's continuous cooling transition (CCT) curve or the JMAK equation, a phase transformation model is established that can dynamically adjust to the actual cooling rate. For different types of phase transformation processes, diffusion-controlled and shear-controlled, models such as the Koistinen–Marburger equation can be used to address these processes. These models are explicitly coupled with the temperature field to form an iterative solution mechanism, enabling real-time feedback on the phase transformation process and temperature evolution.

[0136] (S153) Construction of a parameterized database for steel grades: Build a phase transformation database covering a variety of common steel grades (e.g., low-carbon steel, medium-carbon steel, and high-carbon steel). This database includes the temperature-dependent relationships of density, specific heat capacity, and thermal conductivity, the critical temperature ranges and latent heat values ​​for each phase transformation stage, and phase transformation kinetic model parameters. The model can select the appropriate parameter set for prediction based on the actual steel grade in production.

[0137] (S154) Coupling method with heat conduction model: The latent heat of phase change can be coupled with the energy equation through an explicit heat source term to simplify the calculation process.

[0138] (S155) Model Validation and Application Expansion: The model's phase transformation temperature and microstructure evolution results are verified and calibrated through experimental measurements (e.g., thermal dilatometer, DSC testing, metallographic analysis, etc.) to ensure applicability to different steel grades under different cooling paths. Further exploration can be conducted by combining the phase transformation model with microstructure prediction and mechanical property regression models to construct a multi-scale correlation pathway from temperature to microstructure to performance, providing more comprehensive decision support for hot rolling process control.

[0139] Through the above implementation method, the blind spots of the traditional temperature prediction control model in the phase change stage can be effectively supplemented, and the adaptability of the model to complex cooling behaviors can be enhanced. It is particularly suitable for product process scenarios with strict temperature control requirements such as high-strength steel and alloy steel, and can further improve product performance consistency and process control accuracy.

[0140] Traditional temperature control methods typically rely on fixed cooling strategies and lack the ability to predict and provide feedback on plate temperature changes under complex process conditions. This results in poor finishing inlet temperature stability and significant fluctuations in product performance. The finishing inlet temperature prediction and control method provided in the above-mentioned embodiments addresses technical issues such as low finishing inlet temperature control accuracy during hot rolling and difficulty adapting to temperature fluctuations caused by the dynamic changes in plate materials and thicknesses.

[0141] Furthermore, through the methods provided in the above embodiments, the present invention achieves the following technical effects: 1. Improved finishing rolling entrance temperature control accuracy: By building a temperature prediction control model based on historical data and dynamically adjusting model parameters in combination with real-time data, the temperature prediction is made closer to the actual working conditions, thereby improving control accuracy.

[0142] 2. Enhanced adaptability and robustness: For plates of different materials, thicknesses and cooling conditions, the system can automatically identify and adjust the control strategy to improve adaptability under changing process conditions.

[0143] 3. Optimized the operating efficiency of the cooling system: Based on the deviation between the model prediction results and the target temperature distribution, the cooling system parameters are dynamically adjusted to achieve intelligent allocation and efficient utilization of cooling resources.

[0144] 4. Improved product quality stability: By precisely controlling the finishing rolling inlet temperature, the uneven organizational properties caused by temperature fluctuations are reduced, which helps to improve the mechanical properties and surface quality of hot-rolled plates.

[0145] In summary, the present invention provides a finishing rolling inlet temperature prediction and control method with self-learning ability and dynamic feedback adjustment mechanism, which significantly improves the automation and intelligence level in the hot rolling production process.

[0146] Based on the same inventive concept, the present application also provides a finishing rolling inlet temperature forecast control device, see Figure 3 As shown, the device includes: A model building unit 310 is configured to build a temperature prediction control model based on historical data of the hot rolling cooling process of different plates, the historical data including the material and thickness of the plates transferred from the rough rolling outlet to the finishing rolling inlet, and temperature change data under corresponding cooling conditions; The model optimization unit 320 is used to dynamically adjust the parameters of the temperature prediction control model based on the real-time collected temperature data and the output results of the temperature prediction control model; The temperature control unit 330 is used to adjust the parameters of the cooling system to control the cooling temperature at the finishing rolling entrance based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution.

[0147] The finishing rolling inlet temperature forecast control device provided in the embodiment of the present application can be specific hardware on the equipment or software or firmware installed on the equipment. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for parts not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here. The finishing rolling inlet temperature forecast control device provided in the embodiment of the present application has the same technical features as the finishing rolling inlet temperature forecast control method provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0148] An embodiment of the present application further provides an electronic device. Specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and when the computer program is run by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0149] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present application, the electronic device 400 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0150] Memory 41 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between the system network element and at least one other network element is achieved through at least one communication interface 43 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0151] The bus 42 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, and the like. For ease of representation, Figure 4 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.

[0152] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the process definition device disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0153] Processor 40 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 40. The above processor 40 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 gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may 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, or the like. The storage medium is located in the memory 41 , and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0154] Corresponding to the above method, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above method.

[0155] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device 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.

[0156] In addition, 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 the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0158] It should be noted that if the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0159] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0160] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A finishing rolling inlet temperature prediction and control method, characterized in that: The method comprises: A temperature prediction control model is constructed based on historical data of the hot rolling cooling process of different plates, including the material, thickness and temperature change data of the plates transferred from the rough rolling outlet to the finishing rolling entrance under corresponding cooling conditions; Dynamically adjusting the parameters of the temperature prediction control model according to the real-time collected temperature data and the output result of the temperature prediction control model; Based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution, the parameters of the cooling system are adjusted to control the cooling temperature at the finishing rolling entrance.

2. The finishing rolling inlet temperature prediction and control method according to claim 1, characterized in that: The input parameters of the temperature prediction control model include: initial rolling outlet temperature, temperature learning coefficient, time difference, radiation ratio, specific heat and specific gravity; the output parameters of the temperature prediction control model include finishing rolling inlet temperature; the temperature prediction control model predicts the temperature distribution of each plate in the current cooling process by calculating the average value of the finishing rolling inlet temperature.

3. The finishing rolling inlet temperature prediction and control method according to claim 2, characterized in that: The method for obtaining the input parameters of the temperature prediction control model includes: Determining the initial rolling outlet temperature of the plate using data collected by an infrared pyrometer; determining the temperature learning coefficient based on the ambient temperature, the plate temperature and the stage coefficient at different cooling stages; Determine the time difference by using a first time stamp of the plate temperature collection point arriving at the preliminary rolling exit and a second time stamp of the plate temperature collection point arriving at the finishing rolling entrance; Determine the value of the radiation ratio corresponding to the plate in the current cooling stage by using a preset relationship model between the radiation ratio and the plate characteristics; Determining the specific heat value of the plate at the current cooling stage based on a relationship curve between specific heat and temperature determined in advance through experiments; The specific gravity of the plate is determined according to the material of the plate.

4. The finishing rolling inlet temperature prediction and control method according to claim 3, characterized in that: Dynamically adjusting the parameters of the temperature prediction control model according to the real-time collected temperature data and the output result of the temperature prediction control model includes: comparing the predicted finishing rolling inlet temperature output by the temperature prediction control model with the actually measured finishing rolling inlet temperature, and calculating the temperature deviation between the two; According to the size and change trend of the temperature deviation, a feedback control algorithm is used to dynamically correct the temperature learning coefficient; When the temperature deviation exceeds a preset threshold, at least one of the input parameters, namely, the ambient temperature, the radiation ratio, the specific heat, or the time difference, is recalibrated.

5. The finishing rolling inlet temperature prediction and control method according to claim 1, characterized in that: Adjusting the parameters of the cooling system based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution to control the cooling temperature at the finishing rolling entrance includes: Predicting the temperature distribution during the current cooling process using the adjusted temperature prediction control model; Comparing the predicted temperature distribution result with a set target temperature distribution; According to the range of temperature deviation beyond the standard value in the comparison results, the parameter adjustment strategy of the cooling system is determined to control the cooling temperature at the finishing rolling entrance.

6. The finishing rolling inlet temperature prediction and control method according to claim 5, characterized in that: The parameters of the cooling system include: cooling wind speed, cooling time and injection flow rate; determining the parameter adjustment strategy of the cooling system includes: According to the structure of the finishing rolling entrance area, a three-dimensional geometric model of a cooling system is constructed; the cooling system includes a nozzle arranged on the conveying path of the plate, and the nozzle is used to spray air-water atomization onto the plate; Based on the target temperature of the current cooling stage and the preset cooling parameters, the cooling process of the plate is simulated using the three-dimensional geometric model; The parameter adjustment strategy of the cooling system is optimized based on the simulation results.

7. The finishing rolling inlet temperature prediction and control method according to claim 6, characterized in that: Optimizing the parameter adjustment strategy of the cooling system based on the simulation results includes: Determining, based on the simulation results, the effects of different nozzle layouts, spray velocities, and spray angles on the cooling uniformity and cooling efficiency of the plate; Based on the impact analysis results, a cooling parameter adjustment strategy is generated, which includes: adjusting the distribution density and arrangement of the nozzles on the transmission path of the plate; and adjusting the injection speed, injection angle and / or injection time of the nozzles.

8. A finishing rolling inlet temperature prediction and control device, characterized in that: The device comprises: A model building unit is used to build a temperature prediction control model based on historical data of the hot rolling cooling process of different plates, wherein the historical data includes the material and thickness of the plates transferred from the rough rolling outlet to the finishing rolling entrance, as well as the temperature change data under the corresponding cooling conditions; A model optimization unit, configured to dynamically adjust the parameters of the temperature prediction control model based on the real-time collected temperature data and the output result of the temperature prediction control model; The temperature control unit is used to adjust the parameters of the cooling system based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution, so as to control the cooling temperature at the finishing rolling entrance.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method according to any one of claims 1 to 7.

Images