Steelmaking production scheduling method and system based on digital twinning and medium

Abstract

The invention belongs to the technical field of steelmaking production scheduling, and provides a steelmaking production scheduling method and system based on digital twinning and a medium. According to the method, a continuous casting billet digital twin body is constructed, dynamic coupling analysis is conducted on cutting action and roller way conveying, and the matching performance of cutting and hot charging rhythms is judged; aiming at the mismatching condition, calculating the backlog driving force by utilizing a car-following model, and activating a dynamic buffer area in combination with a state intensity-spatial distance model; the casting blank temperature drop rate is corrected based on the heat transfer theory and the thermal radiation physical field model, and the hot charging fitness is evaluated; and establishing a space-time constraint scheduling model, and dynamically optimizing casting blank generation scheduling. The system comprises a matching identification module, a buffer establishment module, a hot charging analysis module, an adaptation analysis module and a rhythm adjustment module. According to the scheme, the continuous casting billet cutting is matched with the hot charging rhythm, and the hot charging fitness and the production efficiency are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of steelmaking production scheduling, and specifically relates to a steelmaking production scheduling method, system and medium based on digital twin. Background Art

[0002] In the steelmaking process, the efficient coordination of continuous casting billet cutting and hot charging is a key step in improving production efficiency and reducing energy consumption. Current steelmaking production scheduling technology has the following shortcomings in practical application.

[0003] Traditional production scheduling methods struggle to quantify the timing relationship between cutting actions and roller conveying in real time. They also lack the ability to analyze the dynamic coupling between the cutting ignition step signal and the roller deceleration inflection point. This results in inaccurate matching between the cutting deceleration and roller speed adjustment. For example, a time difference between the cutting gun ignition moment and the roller deceleration moment can easily lead to billet stacking or substandard hot charging temperatures, which existing technologies cannot achieve through quantitative analysis.

[0004] Existing scheduling models often treat time constraints and spatial resource allocation independently, without establishing a mechanism for optimizing hot-charging adaptability and spatiotemporal parameters. For example, time windows and buffer capacity cannot be dynamically adjusted based on hot-charging quality requirements. This makes it difficult to balance production efficiency and hot-charging quality in scheduling strategies for cutting time, transport speed, and furnace loading sequence, leading to energy waste and the risk of process imbalance.

[0005] To this end, the present invention provides a steelmaking production scheduling method, system and medium based on digital twin. Summary of the Invention

[0006] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0007] The technical solution adopted by the present invention to solve the technical problem is: a steelmaking production scheduling method, system and medium based on digital twin, including: A steelmaking production scheduling method based on digital twins, comprising: A twin of the ingot is constructed using a digital twin algorithm. Dynamic coupling analysis is performed on the cutting sequence of the twin ingot and the roller conveying rate to determine whether the continuous casting ingot cutting optimization matches the hot charging rhythm. If there is no match, a following model is constructed, and the backlog driving force is calculated by combining the cutting and roller parameters. Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state. If so, a state strength-spatial distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer is activated according to the matching degree. A temperature drop model is established for the dynamic buffer zone to obtain the temperature drop rate of the ingot. Combined with the deceleration accumulation trend correction analysis, the theoretical temperature drop is obtained to determine whether the hot charging requirements are met. If it is not satisfied, the temperature drop rate of the billet is corrected based on the physical field model of thermal radiation coupling, and the hot charging adaptability is evaluated through the dynamic threshold of multi-source data to obtain the hot charging adaptability; A temperature drop compensation strategy integrating phase change and radiation correction parameters is constructed, and a spatiotemporal constraint scheduling model is established in combination with hot charging adaptability to dynamically schedule continuous casting billet production and optimize the matching of billet cutting and hot charging rhythm.

[0008] Furthermore, the dynamic coupling analysis of the cutting action sequence of the twin bodies of the casting and the roller conveying rate is performed as follows: Collect the step signal at the ignition moment of the billet cutting process, extract the high-frequency characteristics of the ignition moment from the step signal, and establish the cutting action signal; Obtain the speed of the roller track and construct the roller track speed curve, identify the speed reduction inflection point of the roller track speed curve through the differential method, and establish the roller track response signal when the roller track speed curve contains the inflection point; Performing signal preprocessing on the cutting action signal and the roller response signal to obtain a cross-correlation function value of the preprocessed cutting action signal and the roller response signal; Determine the coupling deviation point between the cutting rate curve and the roller rate curve based on the cross-correlation function value, perform morphological analysis on the two curves at the coupling deviation point, and obtain the morphological difference value; Based on the morphological difference value and slope response matching degree, the rhythm matching criterion is set to judge whether the continuous casting billet cutting optimization matches the hot charging rhythm.

[0009] Furthermore, the coupling deviation point is determined as follows: The index value at the maximum value is obtained based on the maximum value point of the cross-correlation function value, and the product is calculated by the set sampling period to obtain the coupling time difference; The coupling deviation points are extracted based on the coupling time difference, mapped to the cutting rate curve and the roller rate curve, and the combination of the two curves is divided into timely segment, delayed segment and abnormal segment.

[0010] Furthermore, the morphological difference value is obtained as follows: Obtain the slope response matching degree between the cutting deceleration starting point of the delay section cutting rate curve and the roller speed reduction inflection point of the roller rate curve; The Fréchet distance between the cutting rate curve in the delay section and the roller rate curve was calculated to obtain the morphological difference value.

[0011] Furthermore, the method for judging whether the billet queue movement is in the billet backlog state is as follows: Based on the core equation of the billet queue, a following model is constructed to obtain the billet acceleration; Based on the following model, the acceleration of the casting billet and the feeding speed of the downstream hot charging furnace are obtained to calculate the backlog driving force; Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state.

[0012] 6. The steelmaking production scheduling method based on digital twin according to claim 1, characterized in that the buffer decision position matching analysis of the billet backlog state is performed in the following manner: Construct a state intensity-spatial distance fusion model to obtain the buffer matching degree; Based on the buffer matching degree, the buffer zone judgment decision is made.

[0013] Furthermore, the hot packing adaptability is obtained by: Combined with the Stefan-Boltzmann law, the radiation heat flux between adjacent ingots is calculated; Based on the radiation heat flow between adjacent ingots, the temperature drop rate model is modified; By building a threshold generation network model, the dynamic rate threshold is obtained by inputting the billet characteristic parameter vector into the threshold generation network. The temperature drop consistency coefficient is obtained by numerical analysis based on the dynamic rate threshold and the temperature drop rate; The temperature drop consistency coefficient and the hot installation temperature compliance rate are summed to obtain the hot installation adaptability.

[0014] Furthermore, the method of establishing a time-space constraint scheduling model in combination with hot-loading adaptability is as follows: Quantify the degree of time exceeding the window and establish time constraint control; Quantify buffer zone tension and establish spatial constraint control; Combine time and space constraint control to establish the target fusion function.

[0015] A steelmaking production scheduling system based on digital twins includes the following modules: Matching Identification Module: This module obtains the continuous casting billet cutting timing data and roller operation parameters, and constructs a billet twin using a digital twin algorithm. It then performs a dynamic coupling analysis of the billet twin's cutting action timing and roller conveying rate to determine whether the continuous casting billet cutting optimization matches the hot charging rhythm. Buffer establishment module: If there is no match, a following model is constructed, and the backlog driving force is calculated based on the cutting and roller parameters. Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state. If so, a state strength-spatial distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer is activated according to the matching degree. Hot charging analysis module: establishes a temperature drop model for the dynamic buffer zone to obtain the temperature drop rate of the ingot. Combined with the deceleration accumulation trend correction analysis, the theoretical temperature drop is obtained. Based on the theoretical temperature drop, the temperature after retention is calculated and compared with the hot charging temperature range to determine whether it meets the hot charging requirements. Adaptability analysis module: If the conditions are not met, the temperature drop rate of the billet is corrected based on the physical field model of thermal radiation coupling, and the hot charging adaptability is evaluated through the dynamic threshold of multi-source data to obtain the hot charging adaptability; Rhythm adjustment module: Constructs a temperature drop compensation strategy that integrates phase change and radiation correction parameters, establishes a time-space constraint scheduling model based on hot charging adaptability, dynamically schedules continuous casting billet production, and optimizes the matching of billet cutting and hot charging rhythm.

[0016] The beneficial effects of the present invention are as follows: 1. Build a digital twin of the continuous casting billet through 3D modeling. Combined with on-site sensor data, the virtual mirror is calibrated in real time. Dynamic coupling analysis of the cutting action and roller conveyor rate is performed. This can capture the time deviation and curve morphology differences between cutting and roller deceleration, providing a quantitative basis for judging the matching of cutting and hot charging rhythms, reducing the problem of hot charging temperature not meeting the standard due to timing mismatch, and improving the real-time and accuracy of production rhythm analysis. A following model is constructed to describe the movement of the billet queue, introducing safety spacing constraints and combining cutting and roller parameters to calculate the backlog driving force. Buffer matching is evaluated through a state intensity and spatial distance fusion model, achieving hierarchical activation and scheduling of dynamic buffer zones. This can predict the risk of billet backlog in advance, optimize buffer resource allocation, effectively alleviate production congestion, and improve production space utilization and process smoothness.

[0017] 2. A temperature drop model is established based on heat transfer theory. The estimated retention time is corrected based on the deceleration and accumulation trend of the billet queue. By integrating the theoretical temperature drop and comparing it with the hot charging temperature range, the temperature change of the billet in the dynamic buffer zone can be predicted, ensuring that the temperature of the billet after retention meets the hot charging process requirements, providing temperature protection for the hot charging process, and reducing production losses caused by uncontrolled temperature drop. The thermal radiation coupled physical field model is used to correct the billet temperature drop rate, considering the influence of radiation heat flow and phase change latent heat between adjacent billets. The hot charging adaptability is dynamically evaluated based on multi-source data. This can more clearly reflect the hot charging adaptability of the billet, provide a scientific quality assessment basis for subsequent scheduling decisions, and improve the stability of the hot charging process and the product qualification rate.

[0018] 3. Construct a temperature drop compensation strategy that integrates phase change and radiation correction parameters, establish a time-space constraint scheduling model based on hot charging adaptability, and optimize parameters such as cutting time, transportation speed, and charging sequence through intelligent algorithms to achieve dynamic scheduling of continuous casting billet production, match the cutting and hot charging rhythms, improve production efficiency, reduce energy consumption and production costs, and take into account both process quality and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention will be further described below with reference to the accompanying drawings.

[0020] Figure 1 This is a flow chart of a steelmaking production scheduling method based on digital twins according to an embodiment of the present invention; Figure 2 This is a flow chart of establishing a spatiotemporal constraint scheduling model in combination with hot-loading adaptability according to an embodiment of the present invention; Figure 3 It is a module diagram of a steelmaking production scheduling system based on digital twins described in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0022] Example 1:

[0023] See also Figure 1 As shown, a steelmaking production scheduling method based on digital twin according to an embodiment of the present invention includes the following steps: S1. Obtain the continuous casting billet cutting timing data and roller operation parameters, and construct the billet twin through the digital twin algorithm. Perform dynamic coupling analysis on the billet twin's cutting action timing and roller conveying rate to determine whether the continuous casting billet cutting optimization matches the hot charging rhythm. Among them, the method of constructing the twin of the casting billet through the digital twin algorithm is: Preferably, a geometric model of the continuous casting billet is constructed according to actual size using 3D modeling software, and virtual entities of associated equipment such as rollers and cutting guns are simultaneously established. The heat conduction equations of the thermal conductivity and specific heat capacity of the steel grade are embedded in the virtual entities, and a physical model is constructed in combination with the roller friction and cutting resistance. The physical model is connected to the temperature, position, and velocity data collected in real time by sensors on the casting site through the OPCUA protocol. The collected data is subjected to data noise reduction and temporal and spatial alignment using the Kalman filter algorithm. The convective heat transfer coefficient and friction damping coefficient are iteratively calibrated based on actual production data. By forming a virtual mirror image synchronized with the physical entity state in real time, the casting twin is used to support dynamic simulation and coupled analysis of the cutting action and roller conveying process. Among them, the sensors at the casting site include: thermocouples, encoders, and laser rangefinders; Among them, the method of dynamic coupling analysis of the cutting action sequence of the ingot twin and the roller conveying rate is as follows: Preferably, the timestamps of the cutting gun encoder and the roller speed sensor are obtained, and the timestamps are time-calibrated to within ±10ms; Collect the step signal at the ignition moment of the billet cutting process, extract the high-frequency characteristics of the ignition moment from the step signal, and establish the cutting action signal x(n); Obtain the speed of the roller and construct a roller speed curve. Identify the deceleration inflection point of the roller speed curve by differential method, and establish the roller response signal y(n) at the inflection point of the roller speed curve. Where n is the index value of the signal sequence. It is used to represent different positions in the signal sequence during the process of establishing the cutting action signal x(n), the roller response signal y(n), and calculating the cross-correlation function. The cutting action signal and the roller response signal are preprocessed, and the preprocessed cutting action signal and the roller response signal are connected by establishing a cross-correlation function: , get the cross-correlation function value ; Wherein, k is the limited time offset, and N is the length of the cutting action signal and the roller response signal; Get the maximum value point k of the cross-correlation function max , through the formula: Get the coupling time difference; It is understandable that k max is the cross-correlation function The index value when the maximum value is obtained represents the sampling point offset of the signal roller response signal y(n) relative to the cutting action signal x(n); the cross-correlation function Used to measure the similarity of two signals, cutting action signal x(n) and track response signal y(n), under different time delays; When there is a dynamic correlation between the cutting action (such as ignition) and the roller speed change (such as speed reduction), the maximum point of the cross-correlation function can directly reflect the best time matching position between the two, that is, the coupling time difference; The coupling deviation points are extracted based on the coupling time difference, mapped to the cutting rate curve and the roller rate curve, and the combination of the two curves is divided into timely segment, delayed segment, and abnormal segment; Obtain the slope response matching degree between the cutting deceleration starting point of the delay section cutting rate curve and the roller speed reduction inflection point of the roller rate curve; It should be explained that based on the coupling time difference, the time difference is converted into the time axis deviation of the cutting rate curve and the roller rate curve, so as to determine the specific position of the coupling deviation point on the two curves; by setting the time difference threshold (such as ±50ms for the timely segment, 50-100ms for the delayed segment, and >100ms for the abnormal segment, the threshold can be adjusted according to historical production data statistics or process requirements), the curve segment corresponding to the coupling deviation point is divided into the timely segment, the delayed segment or the abnormal segment; within the delay segment, the cutting rate curve and the roller rate curve are first smoothed and denoised, and then the cutting deceleration starting point and the roller deceleration inflection point are identified by the differential method, and the slope values ​​k1 and k2 at the two points are calculated. The slope response matching degree is obtained using the formula "1-|k1-k2| / max(|k1|,|k2|)" to quantify the synchronization of the deceleration trends of the two. Calculate the Fréchet distance between the delay section cutting rate curve and the roller speed curve to obtain the morphological difference value; Based on the morphological difference value and slope response matching degree, the rhythm matching criteria are set to determine whether the continuous casting billet cutting optimization matches the hot charging rhythm; For example, when the coupling time difference during the cutting process of a continuous casting slab is 80ms, it is determined to be in the delay stage. The slope of the cutting deceleration starting point is extracted as -0.8m / s², and the slope of the roller deceleration inflection point is -0.5m / s². The slope response matching degree is calculated as 1-|(-0.8)-(-0.5)| / max(|-0.8|,|-0.5|)=0.625. At the same time, the Fréchet distance of the delay segment curve is calculated and normalized to obtain a morphological difference value of 0.45. If the set rhythm matching criterion is "when the slope response matching degree is less than 0.7 and the morphological difference value is greater than 0.4, the rhythm is judged to be mismatched", then because the current slope matching degree is 0.625 less than 0.7 and the morphological difference value is 0.45 greater than 0.4, it is judged that the continuous casting billet cutting optimization and the hot charging rhythm do not match, indicating that the slope synchronization of the cutting deceleration and the roller speed reduction is insufficient and the curve morphology is quite different. It is necessary to adjust the cutting gun feed parameters or the roller rate control strategy to optimize the dynamic coupling state.

[0024] It needs to be explained that the role of judging whether the continuous casting billet cutting optimization matches the hot charging rhythm is: Function 1: Triggering backlog risk warning and dynamic buffer scheduling: When the coupling time difference between cutting deceleration and roller speed reduction exceeds the threshold and the slope matching is insufficient, it indicates that the dynamic coordination between the two has failed, which can easily lead to billet queue accumulation. By identifying this mismatch, the following model can be activated to calculate the backlog driving force. Combined with the state strength-spatial distance model, buffer resources can be dynamically allocated (such as adjusting the downstream roller speed and activating the temporary storage area in front of the heating furnace), reducing production congestion caused by rhythm mismatch and improving buffer utilization. Function 2: Start temperature drop anomaly correction and hot charging adaptability assessment: Rhythm mismatch is often accompanied by extended billet retention time or fluctuating conveying rate, resulting in excessive temperature drop. By identifying the mismatch, the billet temperature drop rate can be corrected based on the thermal radiation physical field model, and the hot charging adaptability can be dynamically assessed by combining multiple sources of data such as steel grade composition and backlog driving force to reduce temperature drop prediction errors; Function 3: Driving time-space constraint scheduling and full-process collaborative optimization: After identifying mismatches, a temperature drop compensation strategy integrating phase change and radiation parameters is constructed to adjust parameters such as cutting time, transportation speed, and loading sequence in a coordinated manner.

[0025] S2. If there is no match, a following model is constructed, and the backlog driving force is calculated by combining the cutting and roller parameters. Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state. If so, a state strength-spatial distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer is activated according to the matching degree. Among them, the method of obtaining the backlog forecast point is: The core equation of the casting queue is: Construct a car-following model to describe the motion of the billet queue; in, is the acceleration of the i-th casting billet, is the speed of the billet at time t, To set the base speed of the casting billet, is the initial acceleration of the billet, represents the actual distance between the i-th billet and the preceding billet or a specific reference object at time t; is the safety distance constraint function, through the equation: Establish a safety distance constraint function; Among them, s0 is the minimum safety distance; Preferably, the minimum safety distance is 1.2 times the length of the billet itself; Among them, through the formula: Get the corrected reaction time, They are original reaction time, coupling time difference influence coefficient, and coupling time difference respectively; By formula: Get the maximum deceleration adjustment ; in, They are the original maximum deceleration, slope influence coefficient, cutting deceleration starting point slope, and roller speed reduction inflection point slope; Based on the following model, the acceleration of the casting billet and the feeding speed of the downstream hot charging furnace are obtained to calculate the backlog driving force; Preferably, by the formula: Get the backlog driving force Fy; Among them, k1 and k2 are preset weight coefficients, a i is the billet acceleration, v i is the moving speed of the casting sequence, v r is the speed of the downstream hot charging furnace, Za is the number of billets in the billet queue; Judging whether the billet queue movement is in a billet backlog state based on the backlog driving force; It can be understood that the calculated driving force is compared with the driving force threshold determined based on historical backlog event statistics. If the backlog driving force is higher than or equal to the preset driving force threshold, and the billet acceleration is continuously negative, and the distance between the front and rear billets is less than the safe distance, then it is determined to be in a billet backlog state. If the billet is in a backlog state, a buffer decision position matching analysis is performed on the billet backlog state to make a judgment and decision on the buffer zone; Among them, the method of performing buffer decision position matching analysis on the billet backlog state is: Preferably, by the formula: Construct the state intensity-spatial distance fusion model and obtain the buffer matching degree Mj; Among them, Fyz is the driving force threshold, d j is the Euclidean distance between the center of the billet backlog and the preset buffer zone, is the distance attenuation coefficient; Preferably, the distance attenuation coefficient is 5% of the total length of the roller track; n j In order to alleviate the average time consumption of similar backlog points, C j is the dimensionless maximum number of buffer billets, T j The time from buffer activation to response; Make buffer zone decisions based on buffer matching; For example, the buffers are sorted from high to low in terms of buffer matching, and the buffer with the largest buffer matching degree is selected for activation: If the buffer matching degree is ≥0.7: immediately activate the first-level buffer zone and adjust the downstream roller speed; If 0.5<buffer matching degree<0.7: start preheating of secondary buffer, such as temporary storage area in front of heating furnace; If the buffer matching degree is ≤0.5: trigger remote dispatch, such as calling the spare roller conveyor; It is important to explain that the buffer matching quantifies the dynamic buffer's ability to adapt to the billet backlog state. The ratio of the backlog driving force to the driving force threshold reflects the relative severity of the current billet queue backlog risk. The greater the backlog driving force, the more significant the mismatch between billet acceleration and downstream hot charging furnace speed, and the stronger the backlog trend. This indicator is directly related to the scheduling pressure that the buffer needs to bear. Example 2:

[0026] like Figure 1 As shown, a steelmaking production scheduling method based on digital twins also includes the following steps: S3. Establish a temperature drop model for the dynamic buffer zone to obtain the temperature drop rate of the ingot. Combined with the deceleration accumulation trend correction analysis, the theoretical temperature drop is obtained. The temperature after retention is calculated based on the theoretical temperature drop, and compared with the hot charging temperature range to determine whether it meets the hot charging requirements. Based on heat transfer theory, a temperature drop rate model is established: Get the temperature drop rate ; in, is the preset comprehensive heat transfer coefficient, which is related to the insulation properties of the buffer zone. A / V is the dimensionless ratio of the surface area to the volume of the ingot, reflecting the heat dissipation efficiency. T am is the ambient temperature, T is the temperature of the casting billet; The expected residence time of the slab in the dynamic buffer zone is integrated based on the temperature drop rate to obtain the theoretical temperature drop. The method for obtaining the expected residence time of the billet is as follows: If the billet acceleration is less than 0, that is, the billet queue shows a deceleration and accumulation trend, the formula is: Get the estimated residence time after trend correction ; in, The original expected residence time of the slab, the current speed, the initial speed, and the acceleration of the slab queue output by the following model; It can be understood that the original expected residence time of the slab is obtained by comparing the dynamic buffer zone with the processing rate of the buffer zone; The temperature of the billet after the expected residence time is calculated based on the theoretical temperature drop, and compared with the temperature range of the hot charging stage. If the temperature after the expected residence time is within the temperature of the hot charging stage, the requirements of the hot charging stage are met, otherwise it is not met; S4. If not, the temperature drop rate of the ingot is modified based on the physical field model of thermal radiation coupling, and the hot charging adaptability is evaluated through the dynamic threshold of multi-source data to obtain the hot charging adaptability; Among them, the method of correcting the temperature drop rate of the billet based on the physical field model of thermal radiation coupling is: Preferably, the radiation heat flux Qrad between adjacent ingots is calculated in combination with the Stefan-Boltzmann law; Among them, through the formula: Radiation heat flux Qrad between adjacent ingots; is the surface emissivity of the billet (0.8~0.9 for carbon steel), is the Stefan-Boltzmann constant, A is the radiation heat transfer surface area, 、 Adjacent ingots temperature; The temperature drop rate model is modified based on the radiation heat flux Qrad between adjacent ingots; Preferably, the temperature drop rate model is modified by injecting a radiation correction term: Make corrections; Where m is the mass of the ingot, Cp is the specific heat capacity of the ingot; The hot-install fitness evaluation method based on dynamic thresholds of multi-source data is as follows: Preferably, a threshold generation network model is constructed, and the casting slab characteristic parameter vector is input into the threshold generation network to obtain a dynamic rate threshold; The construction method of the billet characteristic parameter vector is: Obtain the chemical composition, backlog driving force, and safety distance of the ingot steel grade, perform normalization processing on them, and construct the ingot feature vector; Obtain the temperature drop consistency coefficient and the hot installation temperature compliance rate, and sum them to obtain the hot installation adaptability; Among them, through formula 1: Get the temperature drop consistency coefficient ; Through formula 2: Get the temperature compliance rate ; Where T is the casting temperature, T d T is the lower limit of the temperature of the casting billet, opt The target temperature for hot charging of the slab; It should be explained that hot charging adaptability is a comprehensive indicator that measures the degree of match between the temperature state of the continuous casting billet during the hot charging process and the hot charging process requirements. By quantifying the temperature drop consistency and temperature compliance rate, it is used to evaluate whether the billet is suitable for direct hot charging, providing a key basis for production scheduling decisions. Temperature Drop Consistency Coefficient: This reflects the degree of agreement between the actual temperature drop rate of the billet and the expected temperature drop rate. The higher the coefficient, the more stable the temperature drop pattern of the billet during retention or transportation, and the more consistent it is with the temperature maintenance requirements of the hot charging process. Hot charging temperature compliance rate: This indicates the proportion of ingot temperatures within the allowable temperature range of the hot charging process. The higher the compliance rate, the more the ingot temperature meets the hot charging requirements, and the greater the possibility of directly entering the hot charging process. The role of hot-loading adaptability is: Function 1: Quantify the feasibility of hot charging and provide a dynamic evaluation basis for process decision-making. When the hot charging adaptability is ≥0.7, it indicates that the temperature drop of the ingot is stable and the temperature meets the standard. The hot charging process can be directly executed to reduce additional heating energy consumption. If the adaptability is less than 0.5, the system will correct the temperature drop rate based on the Stefan-Boltzmann law and the phase transformation kinetic equation. For example, when 45# steel is in a backlog state, the actual temperature drop rate is found to be higher than that predicted by the traditional model through radiation heat flow calculation. Combined with the correction of the latent heat effect of phase transformation, the compensation measure of increasing the heating power from 500kW to 650kW is triggered to ensure that the temperature meets the hot charging requirements. Function 2: Drive the spatiotemporal constraint scheduling model to optimize production rhythm matching. Hot charging fitness serves as the core parameter of the target fusion function minZ. By quantifying the degree of time window overshoot and buffer zone tension, the system adjusts the billet cutting time and transportation speed in the temporal dimension to avoid excessive temperature drop due to process delays. In the spatial dimension, the system optimizes the buffer zone allocation strategy, prioritizing billets with high hot charging fitness for entry into the furnace. For example, when the buffer zone tension exceeds the threshold, the system sorts billets by hot charging fitness, temporarily storing billets with low fitness in the secondary buffer zone for preheating, while prioritizing billets with high fitness for entry into the hot charging furnace. A genetic algorithm is used to solve the optimal parameter combination, achieving dynamic matching of the cutting rhythm and hot charging process.

[0027] S5. Construct a temperature drop compensation strategy that integrates phase change and radiation correction parameters, establish a spatiotemporal constraint scheduling model based on hot charging adaptability, dynamically schedule continuous casting production, and optimize the matching of billet cutting and hot charging rhythm; Among them, the method of constructing a temperature drop compensation strategy integrating phase change and radiation correction parameters is as follows: Preferably, the radiation heat flow between the ingots is quantified by the Stefan-Boltzmann law, and the phase change fraction is calculated in combination with the phase change kinetic equation (such as the MAK equation) to achieve the correction of the temperature drop rate; then, based on the corrected temperature drop parameters, the hot charging temperature threshold, and the allowable temperature drop rate, a compensation decision model is established, and compensation measures for adjusting the heating power, heating time, and residence time are formulated for different temperature drop scenarios, forming a closed-loop control strategy so that the temperature drop of the continuous casting ingot meets the hot charging process requirements; For example, when a steel mill produces 45# steel, the traditional model calculates a temperature drop rate of 8°C / min for continuous casting billets in a backlog state. Using the radiation correction model and the Stefan-Boltzmann law, it is found that due to the small spacing between adjacent billets (1.2 times the billet length), the radiation heat flux causes the actual temperature drop rate to reach 10°C / min. At the same time, the ingot was in the 727°C phase transition zone. According to the JMAK equation, the phase transition fraction was calculated to be 0.3. The latent heat of phase transition suppressed the temperature drop, correcting the rate to 9°C / min. However, the allowable temperature drop rate for hot charging of this steel grade is 8.5°C / min. At this point, the compensation strategy was automatically activated: the heating furnace power was increased from 500kW to 650kW, the heating time was extended by 15 minutes, and the roller transport speed was adjusted to allow the ingot to remain in the heating zone for an additional 8 minutes, achieving the required temperature drop rate and meeting the hot charging process requirements. Among them, the method of establishing a time-space constraint scheduling model in combination with hot loading adaptability is as follows: A1. Quantify the degree of time exceeding the window and establish time constraint control; By formula: Quantization time window , used to establish time-constrained control; A2. Quantify buffer zone tension and establish spatial constraint control; By formula: Quantifying buffer capacity strain , used to establish spatial constraint control; A3. Combine time and space constraint control to establish the target fusion function; By formula: Construct the target fusion function minZ; Among them, Fit is the heat-fitting adaptability, It is the preset proportional coefficient of the fusion function, which is set by professionals in this field based on experience; Those skilled in the art will understand that the target fusion function is input into the genetic algorithm for solution. The genetic algorithm can search for the parameter combination that minimizes the target function Z in the complex solution space, and based on the parameter combination, dynamically schedule multiple key links in the continuous casting production process; In terms of time, the slab cutting time and the transportation speed between processes are adjusted according to the calculation results to ensure that the steelmaking production process meets the hot charging time window requirements and reduce the degree of time exceeding the window; In terms of space, the storage location and allocation strategy of the billets in the buffer zone should be rationally planned. Based on the feedback of the buffer zone tension, the furnace loading sequence should be optimized, and billets with high hot charging adaptability should be given priority for hot charging, thereby improving hot charging efficiency and reducing energy consumption. Throughout the production process, a real-time monitoring system continuously monitors changes in hot charging adaptability, time window exceeding, and buffer zone tension. This real-time data is fed back to the scheduling system, enabling continuous optimization and adjustment of scheduling decisions. This closed-loop control approach ensures matching of billet cutting and hot charging rhythms, ensuring production efficiency while improving product quality.

[0028] Example 3:

[0029] like Figure 3 As shown in the figure, a steelmaking production scheduling system based on digital twins includes the following modules: Matching Identification Module: This module obtains the continuous casting billet cutting timing data and roller operation parameters, and constructs a billet twin using a digital twin algorithm. It then performs a dynamic coupling analysis of the billet twin's cutting action timing and roller conveying rate to determine whether the continuous casting billet cutting optimization matches the hot charging rhythm. Buffer establishment module: If there is no match, a following model is constructed, and the backlog driving force is calculated based on the cutting and roller parameters. Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state. If so, a state strength-spatial distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer is activated according to the matching degree. Hot charging analysis module: establishes a temperature drop model for the dynamic buffer zone to obtain the temperature drop rate of the ingot. Combined with the deceleration accumulation trend correction analysis, the theoretical temperature drop is obtained. Based on the theoretical temperature drop, the temperature after retention is calculated and compared with the hot charging temperature range to determine whether it meets the hot charging requirements. Adaptability analysis module: If the conditions are not met, the temperature drop rate of the billet is corrected based on the physical field model of thermal radiation coupling, and the hot charging adaptability is evaluated through the dynamic threshold of multi-source data to obtain the hot charging adaptability; Rhythm adjustment module: Constructs a temperature drop compensation strategy that integrates phase change and radiation correction parameters, establishes a time-space constraint scheduling model based on hot charging adaptability, dynamically schedules continuous casting billet production, and optimizes the matching of billet cutting and hot charging rhythm.

[0030] Example 4:

[0031] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements a steelmaking production scheduling method based on digital twins as described in any one of the above methods.

[0032] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0033] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0034] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0035] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0036] 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.

[0037] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0038] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A steelmaking production scheduling method based on digital twin, characterized by: include: A twin of the ingot is constructed using a digital twin algorithm. Dynamic coupling analysis is performed on the cutting sequence of the twin ingot and the roller conveying rate to determine whether the continuous casting ingot cutting optimization matches the hot charging rhythm. If there is no match, a following model is constructed, and the backlog driving force is calculated by combining the cutting and roller parameters. Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state. If so, a state strength-spatial distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer is activated according to the matching degree. A temperature drop model is established for the dynamic buffer zone to obtain the temperature drop rate of the ingot. Combined with the deceleration accumulation trend correction analysis, the theoretical temperature drop is obtained to determine whether the hot charging requirements are met. If it is not satisfied, the temperature drop rate of the billet is corrected based on the physical field model of thermal radiation coupling, and the hot charging adaptability is evaluated through the dynamic threshold of multi-source data to obtain the hot charging adaptability; A temperature drop compensation strategy integrating phase change and radiation correction parameters is constructed, and a spatiotemporal constraint scheduling model is established in combination with hot charging adaptability to dynamically schedule continuous casting billet production and optimize the matching of billet cutting and hot charging rhythm.

2. The steelmaking production scheduling method based on digital twin according to claim 1, characterized in that: The method of dynamically coupling the cutting action sequence of the twin bodies of the casting and the roller conveying rate is as follows: Collect the step signal at the ignition moment of the billet cutting process, extract the high-frequency characteristics of the ignition moment from the step signal, and establish the cutting action signal; Obtain the speed of the roller track and construct the roller track speed curve, identify the speed reduction inflection point of the roller track speed curve through the differential method, and establish the roller track response signal when the roller track speed curve contains the inflection point; Performing signal preprocessing on the cutting action signal and the roller response signal to obtain a cross-correlation function value of the preprocessed cutting action signal and the roller response signal; Determine the coupling deviation point between the cutting rate curve and the roller rate curve based on the cross-correlation function value, perform morphological analysis on the two curves at the coupling deviation point, and obtain the morphological difference value; Based on the morphological difference value and slope response matching degree, the rhythm matching criterion is set to judge whether the continuous casting billet cutting optimization matches the hot charging rhythm.

3. The steelmaking production scheduling method based on digital twin according to claim 2, characterized in that: The coupling deviation point is determined as follows: The index value at the maximum value is obtained based on the maximum value point of the cross-correlation function value, and the product is calculated by the set sampling period to obtain the coupling time difference; The coupling deviation points are extracted based on the coupling time difference, mapped to the cutting rate curve and the roller rate curve, and the combination of the two curves is divided into timely segment, delayed segment and abnormal segment.

4. The steelmaking production scheduling method based on digital twin according to claim 2, characterized in that: The morphological difference value is obtained as follows: Obtain the slope response matching degree between the cutting deceleration starting point of the delay section cutting rate curve and the roller speed reduction inflection point of the roller rate curve; The Fréchet distance between the cutting rate curve in the delay section and the roller rate curve was calculated to obtain the morphological difference value.

5. The steelmaking production scheduling method based on digital twin according to claim 1, characterized in that: The method for judging whether the billet queue movement is in the billet backlog state is as follows: Based on the core equation of the billet queue, a following model is constructed to obtain the billet acceleration; Based on the following model, the acceleration of the casting billet and the feeding speed of the downstream hot charging furnace are obtained to calculate the backlog driving force; Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state.

6. The steelmaking production scheduling method based on digital twin according to claim 1, characterized in that: The method of performing buffer decision position matching analysis on the billet backlog state is as follows: Construct a state intensity-spatial distance fusion model to obtain the buffer matching degree; Based on the buffer matching degree, the buffer zone judgment decision is made.

7. The steelmaking production scheduling method based on digital twin according to claim 1, characterized in that: The method for obtaining the hot packing adaptability is: Combined with the Stefan-Boltzmann law, the radiation heat flux between adjacent ingots is calculated; Based on the radiation heat flow between adjacent ingots, the temperature drop rate model is modified; By building a threshold generation network model, the dynamic rate threshold is obtained by inputting the billet characteristic parameter vector into the threshold generation network. The temperature drop consistency coefficient is obtained by numerical analysis based on the dynamic rate threshold and the temperature drop rate; The temperature drop consistency coefficient and the hot installation temperature compliance rate are summed to obtain the hot installation adaptability.

8. The steelmaking production scheduling method based on digital twin according to claim 1, characterized in that: The method of establishing a time-space constraint scheduling model based on hot-loading fitness is as follows: Quantify the degree of time exceeding the window and establish time constraint control; Quantify buffer zone tension and establish spatial constraint control; Combine time and space constraint control to establish the target fusion function.

9. A steelmaking production scheduling system based on digital twin, used to implement the steelmaking production scheduling method based on digital twin according to any one of claims 1 to 8, characterized in that: Includes the following modules: Matching Identification Module: This module obtains the continuous casting billet cutting timing data and roller operation parameters, and constructs a billet twin using a digital twin algorithm. It then performs a dynamic coupling analysis of the billet twin's cutting action timing and roller conveying rate to determine whether the continuous casting billet cutting optimization matches the hot charging rhythm. Buffer establishment module: If there is no match, a following model is constructed, and the backlog driving force is calculated based on the cutting and roller parameters. Based on the backlog driving force, it is determined whether the billet queue movement is in a billet backlog state. If so, a state strength-spatial distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer is activated according to the matching degree. Hot charging analysis module: establishes a temperature drop model for the dynamic buffer zone to obtain the temperature drop rate of the ingot. Combined with the deceleration accumulation trend correction analysis, the theoretical temperature drop is obtained. Based on the theoretical temperature drop, the temperature after retention is calculated and compared with the hot charging temperature range to determine whether it meets the hot charging requirements. Adaptability analysis module: If the conditions are not met, the temperature drop rate of the billet is corrected based on the physical field model of thermal radiation coupling, and the hot charging adaptability is evaluated through the dynamic threshold of multi-source data to obtain the hot charging adaptability; Rhythm adjustment module: Constructs a temperature drop compensation strategy that integrates phase change and radiation correction parameters, establishes a time-space constraint scheduling model based on hot charging adaptability, dynamically schedules continuous casting billet production, and optimizes the matching of billet cutting and hot charging rhythm.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the steelmaking production scheduling method based on digital twins described in any one of claims 1 to 8 are implemented.

Images