A steelmaking production scheduling method and system based on digital twinning and a medium

Abstract

The present application 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. The method dynamically couples and analyzes cutting action and roller conveying by constructing a continuous casting billet digital twin, judges the matching of cutting and hot charging rhythm, calculates the backlog driving force by using a car-following model for the mismatching case, activates a dynamic buffer zone in combination with a state intensity-space distance model, corrects the casting billet temperature drop rate based on a heat transfer and thermal radiation physical field model, evaluates the hot charging adaptability, establishes a time-space constraint scheduling model, and dynamically optimizes the continuous casting billet generation scheduling. The system comprises a matching identification module, a buffer establishment module, a hot charging analysis module, an adaptability analysis module, and a rhythm adjustment module. The scheme realizes the matching of continuous casting billet cutting and hot charging rhythm, and improves the hot charging adaptability and production efficiency.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of steelmaking production scheduling, in particular to a steelmaking production scheduling method and system based on digital twinning and a medium. BACKGROUND

[0002] In the steel smelting process, efficient coordination of continuous casting billet cutting and hot charging process is the core link to improve production efficiency and reduce energy consumption. The current steelmaking production scheduling technology has the following deficiencies in actual application.

[0003] The traditional production scheduling method cannot quantitatively correlate the timing of cutting action and roller conveying in real time, lacks dynamic coupling analysis means for cutting point ignition step signal and roller speed reduction inflection point, resulting in insufficient rhythm matching accuracy of cutting deceleration and roller speed adjustment. For example, when there is a time difference between the ignition time of the cutting gun and the roller speed reduction time, it is easy to cause billet conveying accumulation or substandard hot charging temperature, and the existing technology cannot achieve regulation and control through quantitative analysis.

[0004] The existing scheduling model mainly handles time constraints and space resource allocation independently, and does not establish a linkage optimization mechanism for hot charging fitness and space-time parameters. For example, the time window and buffer capacity cannot be dynamically adjusted according to the hot charging quality demand, resulting in difficulty in balancing production efficiency and hot charging quality in the scheduling strategy of cutting time, transportation speed and furnace charging sequence, and there is a risk of energy waste and process imbalance.

[0005] Therefore, the application provides a steelmaking production scheduling method, system and medium based on digital twinning. SUMMARY

[0006] In order to make up for the deficiencies of the prior art and solve at least one technical problem proposed in the background art.

[0007] The technical scheme adopted by the application to solve the technical problems is: a steelmaking production scheduling method, system and medium based on digital twinning, comprising:

[0008] A steelmaking production scheduling method based on digital twinning, comprising:

[0009] A billet twin body is constructed by a digital twinning algorithm, and the timing of the cutting action of the billet twin body and the roller conveying speed are dynamically coupled and analyzed to determine whether the continuous casting billet cutting optimization and the hot charging rhythm match;

[0010] If they do not match, a following model is constructed, and a backlog driving force is calculated in combination with the cutting and roller parameters, and based on the backlog driving force, it is determined whether the billet queue motion is in a billet backlog state, and if it is, a state intensity-space distance fusion model is established to calculate a buffer matching degree, and the corresponding dynamic buffer area is activated according to the matching degree;

[0011] A temperature drop model is established for the dynamic buffer to obtain a slab temperature drop rate, a theoretical temperature drop amount is obtained by combining a deceleration accumulation trend correction analysis, and it is determined whether the hot charging requirement is met;

[0012] If not, the slab temperature drop rate is corrected based on a physical field model coupled with thermal radiation, a hot charging adaptability is evaluated through a multi-source data dynamic threshold, and a hot charging adaptability is obtained.

[0013] A temperature drop compensation strategy is constructed by fusing a phase change-revised parameter, a time-space constraint scheduling model is established by combining the hot charging adaptability, and a continuous casting slab production is dynamically scheduled to optimize the matching of the slab cutting and the hot charging rhythm.

[0014] Further, the cutting action timing of the slab twin and the roller conveying rate are dynamically coupled and analyzed in the following manner:

[0015] A step signal at the ignition moment of the slab cutting process is collected, high-frequency features at the ignition moment are extracted from the step signal, and a cutting action signal is established;

[0016] The rate of the roller operation is obtained and a roller rate curve is constructed, a deceleration inflection point of the roller rate curve is identified through differentiation, and a roller response signal containing the inflection point moment of the roller rate curve is established;

[0017] The cutting action signal and the roller response signal are preprocessed, and the cross-correlation function values of the preprocessed cutting action signal and the roller response signal are obtained;

[0018] Based on the cross-correlation function values, the coupling deviation point of the cutting rate curve and the roller rate curve is determined, the two curves are analyzed in terms of form at the coupling deviation point, and a form difference value is obtained;

[0019] Based on the form difference value and the slope response matching degree, a rhythm matching criterion is set, and it is determined whether the continuous casting slab cutting optimization and the hot charging rhythm are matched.

[0020] Further, the coupling deviation point is determined in the following manner:

[0021] Based on the maximum value point of the cross-correlation function value, the index value at the maximum value moment is obtained, and the product is calculated by multiplying the sampling period, to obtain a coupling time difference;

[0022] Based on the coupling time difference, the coupling deviation point is extracted, the coupling deviation point is mapped to the cutting rate curve and the roller rate curve, and the two curves are combined and correspondingly divided into a timely period, a delay period, and an abnormal period.

[0023] Further, the form difference value is obtained in the following manner:

[0024] The slope response matching degree of the cutting deceleration starting point of the cutting rate curve in the delay period and the roller deceleration inflection point of the roller rate curve is obtained.

[0025] Calculate the Fréchet distance of the delay section cutting rate curve and the roller rate curve to obtain the shape difference value.

[0026] Further, the way to determine whether the movement of the slab queue is in the slab backlog state is:

[0027] Based on the slab queue core equation, a car-following model is constructed to obtain the slab acceleration;

[0028] Based on the car-following model, the slab acceleration and the downstream hot charging furnace feeding speed are obtained to calculate the backlog driving force;

[0029] Based on the backlog driving force, it is determined whether the movement of the slab queue is in the slab backlog state.

[0030] 6. The digital twin-based steelmaking production scheduling method according to claim 1, wherein the way to perform buffer decision position matching analysis on the slab backlog state is:

[0031] A state intensity-space distance fusion model is constructed to obtain a buffer matching degree;

[0032] Based on the buffer matching degree, a judgment decision is made on the buffer zone.

[0033] Further, the way to obtain the hot charging adaptability is:

[0034] The radiation heat flow between adjacent slabs is calculated in combination with the Stefan-Boltzmann law;

[0035] Based on the radiation heat flow between adjacent slabs, the temperature drop rate model is modified;

[0036] By constructing a threshold generation network model, the slab feature parameter vector is input to the threshold generation network to obtain a dynamic rate threshold;

[0037] Based on the dynamic rate threshold, the temperature drop rate is numerically analyzed to obtain a temperature drop consistency coefficient;

[0038] The temperature drop consistency coefficient and the hot charging temperature compliance rate are summed to obtain the hot charging adaptability.

[0039] Further, the way to establish a space-time constraint scheduling model in combination with the hot charging adaptability is:

[0040] Quantify the time window degree to establish a time constraint control;

[0041] Quantify the buffer zone tension to establish a space constraint control;

[0042] In combination with the time and space constraint controls, a target fusion function is established.

[0043] A steelmaking production scheduling system based on digital twinning, comprising the following modules:

[0044] A matching identification module: obtains continuous casting billet cutting timing data and roller running parameters, and constructs a billet twin body through a digital twinning algorithm, dynamically couples and analyzes the cutting action timing of the billet twin body and the roller conveying rate, and judges whether the continuous casting billet cutting optimization and the hot charging rhythm match;

[0045] A buffer establishment module: if not matched, a following model is constructed, and the backlog driving force is calculated in combination with the cutting and roller parameters, and based on the backlog driving force, it is judged whether the billet queue motion is in a billet backlog state, if so, a state intensity-space distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer zone is activated according to the matching degree;

[0046] A hot charging analysis module: a temperature drop model is established for the dynamic buffer zone, the billet temperature drop rate is obtained, the theoretical temperature drop amount is obtained through correction analysis combined with the deceleration accumulation trend, and based on the theoretical temperature drop amount, the temperature after retention is calculated, and whether it meets the hot charging requirement is judged in combination with the hot charging temperature range;

[0047] An adaptive analysis module: if not satisfied, the billet temperature drop rate is corrected based on a physical field model of thermal radiation coupling, and the hot charging adaptability is evaluated through a multi-source data dynamic threshold to obtain the hot charging adaptability;

[0048] A rhythm adjustment module: a temperature drop compensation strategy is constructed by fusing phase change-revised parameters, a time-space constraint scheduling model is established in combination with the hot charging adaptability, the continuous casting billet production is dynamically scheduled, and the matching of the billet cutting and the hot charging rhythm is optimized.

[0049] The beneficial effects of the present application are as follows:

[0050] 1. The continuous casting billet digital twin is constructed by three-dimensional modeling, the virtual mirror image is calibrated in real time in combination with the field sensor data, the cutting action and the roller conveying rate are dynamically coupled and analyzed, the time deviation and curve shape difference of cutting and roller deceleration can be captured, a quantitative basis for judging the matching of cutting and hot charging rhythm is provided, the problem of substandard hot charging temperature caused by time sequence mismatch is reduced, and the real-time and accuracy of production rhythm analysis are improved. The following model is constructed to describe the motion of the billet queue, the safety distance constraint is introduced, the backlog driving force is calculated in combination with the cutting and roller parameters, the buffer matching degree is evaluated through the state intensity and space distance fusion model, the hierarchical activation and scheduling of the dynamic buffer zone are realized, the billet backlog risk can be predicted in advance, the buffer zone resource allocation is optimized, the production congestion is effectively relieved, and the production space utilization and process smoothness are improved.

[0051] 2, based on the theory of heat transfer to establish temperature drop model, combined with the deceleration accumulation trend of the strand queue to correct the expected residence time, through integral calculation of the theoretical temperature drop and comparison with the hot charging temperature range, the temperature change of the strand in the dynamic buffer zone can be predicted, the temperature of the strand after residence can meet the hot charging process requirements, the temperature guarantee for the hot charging link is provided, and the production loss caused by uncontrolled temperature drop is reduced. The heat radiation coupling physical field model is used to correct the temperature drop rate of the strand, the influence of the radiation heat flow between adjacent strands and the latent heat of phase change is considered, combined with the dynamic evaluation of the hot charging adaptability of multiple data sources, the hot charging adaptability of the strand can be more clearly reflected, and scientific quality evaluation basis is provided for subsequent scheduling decision, and the stability of the hot charging process and the product qualification rate are improved.

[0052] 3, build a temperature drop compensation strategy integrating phase change and radiation correction parameters, establish a space-time constraint scheduling model combined with the hot charging adaptability, optimize parameters such as cutting time, transportation speed and furnace charging sequence through intelligent algorithm, realize dynamic scheduling of continuous casting strand production, match the cutting and hot charging rhythm, improve the production efficiency, reduce the energy consumption and production cost, and balance the process quality and economic benefit. BRIEF DESCRIPTION OF DRAWINGS

[0053] The application will be further described below with reference to the drawings.

[0054] Figure 1 is a flow chart of a steelmaking production scheduling method based on digital twinning according to an embodiment of the application;

[0055] Figure 2 is a flow chart of a space-time constraint scheduling model established combined with the hot charging adaptability according to an embodiment of the application;

[0056] Figure 3 is a module diagram of a steelmaking production scheduling system based on digital twinning according to an embodiment of the application. DETAILED DESCRIPTION

[0057] In order to make the technical means, creative features, purposes and effects realized by the application easy to understand, the application will be further described below with reference to the specific embodiments.

[0058] Embodiment 1:

[0059] Please refer to Figure 1 The steelmaking production scheduling method based on digital twinning according to an embodiment of the application includes the following steps:

[0060] S1, acquire the continuous casting strand cutting time sequence data and the roller running parameters, and build the strand twin through the digital twinning algorithm, dynamically couple the cutting action time sequence of the strand twin and the roller conveying rate, and judge whether the continuous casting strand cutting optimization and the hot charging rhythm match;

[0061] The way of constructing the casting blank twin by the digital twin algorithm is:

[0062] Preferably, a continuous casting blank geometric model is constructed according to actual dimensions by a three-dimensional modeling software, a virtual entity of a roller way, a cutting gun and other related devices is synchronously established, a heat conduction equation of a steel grade thermal conductivity coefficient and a specific heat capacity is embedded in the virtual entity, and a physical model is constructed in combination with a roller way friction force and a cutting resistance;

[0063] The physical model is connected to temperature, position and speed data collected by a casting blank field sensor in real time through an OPCUA protocol, the collected data is subjected to data noise reduction and space-time alignment by using a Kalman filtering algorithm, a convection heat transfer coefficient and a friction damping coefficient are iteratively calibrated based on actual production data, a virtual mirror image, i.e., a casting blank twin, which is real-time synchronized with a physical entity state, is formed, and is used to support dynamic simulation and coupling analysis of a cutting action and a roller way conveying process;

[0064] The casting blank field sensor includes a thermocouple, an encoder and a laser range finder.

[0065] The way of dynamically coupling and analyzing the cutting action time sequence of the casting blank twin and the roller way conveying speed is:

[0066] Preferably, the time stamps of the cutting gun encoder and the roller way speed sensor are acquired, and the time stamps are time calibrated to within ±10 ms.

[0067] A step signal of a casting blank cutting process ignition moment is collected, high-frequency features of the ignition moment are extracted from the step signal, and a cutting action signal x(n) is established.

[0068] The speed of the roller way operation is acquired and a roller way speed curve is constructed, a speed reduction inflection point of the roller way speed curve is identified by a differential method, and a roller way response signal y(n) containing the inflection point moment of the roller way speed curve is established.

[0069] n is an index value of a signal sequence. In the processes of establishing the cutting action signal x(n), the roller way response signal y(n) and the cross-correlation function calculation, different positions in the signal sequence are represented.

[0070] The cutting action signal and the roller way response signal are subjected to signal pretreatment, the pretreated cutting action signal and the roller way response signal are subjected to cross-correlation function establishment: , and a cross-correlation function value is acquired.

[0071] k is a limited time offset, and N is the length of the cutting action signal and the roller way response signal.

[0072] The maximum point k of the cross-correlation function value is acquired: max , and the formula: acquiring the coupling time difference;

[0073] It can be understood that k max is a cross-correlation function The index value when the maximum value is obtained represents the sampling point offset of the signal response signal y(n) relative to the cutting action signal x(n); the cross-correlation function is used to measure the similarity of the two signals, the cutting action signal x(n) and the signal response signal y(n), at different time delays;

[0074] When there is a dynamic correlation between the cutting action (such as ignition) and the change in the roller speed (such as speed reduction), the maximum point of the cross-correlation function can directly reflect the best time matching position of the two, i.e. the coupling time difference;

[0075] Based on the coupling time difference, the coupling deviation point is extracted, and the coupling deviation point is mapped to the cutting speed curve and the roller speed curve, and the two curves are combined and correspondingly divided into the timely period, the delay period, and the abnormal period;

[0076] The slope response matching degree of the cutting deceleration starting point of the cutting speed curve in the delay period and the roller speed inflection point of the roller speed curve is obtained;

[0077] It needs to be explained that based on the coupling time difference, the time difference is converted into the time axis deviation of the cutting speed curve and the roller speed curve, so as to determine the specific position of the coupling deviation point on the two curves; by setting a time difference threshold (such as ±50ms for the timely period, 50-100ms for the delay period, and >100ms for the abnormal period, which 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 period, the delay period, or the abnormal period; in the delay period, the cutting speed curve and the roller speed curve are first preprocessed by smoothing and denoising, and then the cutting deceleration starting point and the roller speed inflection point are identified by differential method, the slope values k1 and k2 at the two points are calculated, and the slope response matching degree is obtained by using the formula "1-|k1-k2| / max(|k1|,|k2|)", which quantifies the synchronization of the deceleration trends of the two;

[0078] The Fréchet distance of the cutting speed curve and the roller speed curve in the delay period is calculated to obtain the shape difference value;

[0079] Based on the shape difference value and the slope response matching degree, the rhythm matching criterion is set and it is judged whether the continuous casting billet cutting optimization and the hot charging rhythm match;

[0080] For example, when the coupling time difference is 80 ms during the cutting process of the continuous casting billet, it is determined that it is in the delay section, the slope of the cutting deceleration starting point is -0.8 m / s2, the slope of the roller speed reduction inflection point is -0.5 m / s2, and the slope response matching degree is 1-|-0.8-(-0.5)| / max(|-0.8|,|-0.5|)=0.625;

[0081] At the same time, the Fréchet distance of the delay section curve is calculated and normalized to obtain a shape difference value of 0.45. If the set rhythm matching criterion is “when the slope response matching degree is <0.7 and the shape difference value is >0.4, it is determined that the rhythm is not matched”, then because the current slope matching degree 0.625<0.7 and the shape difference value 0.45>0.4, it is determined that the continuous casting billet cutting optimization and hot charging rhythm are not matched, indicating that the slope synchronization of the cutting deceleration and the roller speed reduction is insufficient and the curve shape difference is large, and the cutting gun feed parameters or the roller speed control strategy need to be adjusted to optimize the dynamic coupling state.

[0082] It needs to be explained that the role of determining whether the continuous casting billet cutting optimization and the hot charging rhythm are matched is:

[0083] Role one, triggering backlog risk early warning and dynamic buffer scheduling: when the coupling time difference of the cutting deceleration and the roller speed reduction exceeds the threshold and the slope matching degree is insufficient, it indicates that the dynamic cooperation of the two is failed, which is easy to cause the accumulation of the billet queue. By identifying the mismatch state, the following model can be activated to calculate the backlog driving force, and the buffer zone resources can be dynamically allocated (such as adjusting the downstream roller speed, starting the pre-storage area in front of the heating furnace) to reduce the production congestion caused by the rhythm mismatch and improve the buffer zone utilization rate;

[0084] Role two, starting the temperature drop abnormal correction and hot charging adaptability evaluation: the rhythm mismatch is often accompanied by the extension of the billet residence time or the fluctuation of the conveying speed, which causes the temperature drop to exceed the standard. By judging the mismatch state, the temperature drop rate can be corrected based on the thermal radiation physical field model, and the hot charging adaptability can be dynamically evaluated based on the steel grade composition, the backlog driving force and other multi-source data to reduce the temperature drop prediction error;

[0085] Role three, driving the space-time constraint scheduling and whole-process collaborative optimization: after identifying the mismatch, a temperature drop compensation strategy that integrates phase change-radiation parameters is constructed to adjust parameters such as cutting time, transportation speed and furnace charging sequence.

[0086] S2, if it is not matched, a following model is constructed, and the backlog driving force is calculated based on the cutting and roller parameters. Whether the billet queue movement is in the billet backlog state is judged based on the backlog driving force. If it is in the billet backlog state, a state strength-space distance fusion model is established to calculate the buffer matching degree, and the corresponding dynamic buffer zone is activated according to the matching degree sorting;

[0087] Among them, the way to get the backlog prediction point is:

[0088] Through the strand queue core equation: A follow-up model is constructed for describing the strand queue movement;

[0089] Wherein, is the acceleration of the i-th strand, is the speed of the strand at time t, is the reference speed of the strand, is the initial acceleration of the strand, is the actual distance between the i-th strand and the front strand or a specific reference object at time t;

[0090] is a safety distance constraint function, which is established by the equation: A safety distance constraint function is established;

[0091] Wherein, s0 is the minimum safety distance;

[0092] Preferably, the minimum safety distance is 1.2 times the length of the strand itself;

[0093] Wherein, the corrected reaction time is obtained by the formula: are the original reaction time, the coupling time difference influence coefficient, and the coupling time difference, respectively;

[0094] The maximum deceleration adjustment amount is obtained by the formula: ;

[0095] Wherein, are the original maximum deceleration, the slope influence coefficient, the cutting deceleration starting slope, and the track deceleration inflection point slope, respectively;

[0096] The strand acceleration is obtained based on the follow-up model, and the downstream hot charging furnace feeding speed is calculated to obtain the accumulation driving force;

[0097] Preferably, the accumulation driving force Fy is obtained by the formula:

[0098] Wherein, k1 and k2 are preset weight coefficients, a i is the strand acceleration, v i is the moving speed of the strand sequence, v r is the speed of the downstream hot charging furnace, and Za is the number of strands in the strand queue;

[0099] Based on the accumulation driving force, it is judged whether the strand queue movement is in the strand accumulation state;

[0100] ​​​It can be understood that the calculated driving force is compared with the driving force threshold value determined based on historical backlog event statistics, if the backlog driving force is higher than or equal to the preset driving force threshold value, and the casting blank acceleration is continuously negative and the spacing between the front and rear casting blanks is less than the safe spacing, it is determined that it is in the casting blank backlog state;

[0101] If it is in the casting blank backlog state, the buffer decision position matching analysis is performed on the casting blank backlog state, and the buffer zone is judged and decided;

[0102] The buffer decision position matching analysis on the casting blank backlog state is performed in the following manner:

[0103] Preferably, the buffer matching degree Mj is obtained by the formula: The state intensity-space distance fusion model is constructed, and the buffer matching degree Mj is obtained.

[0104] Wherein, Fyz is the driving force threshold value, d j is the Euclidean distance between the center of the casting blank backlog state and the preset buffer zone, is the distance attenuation coefficient;

[0105] Preferably, the distance attenuation coefficient is 5% of the total length of the track;

[0106] n j is the average time consumed by the same kind of backlog point, C j is the dimensionless maximum number of buffer casting blanks, T j is the time from the activation of the buffer zone to the response;

[0107] Based on the buffer matching degree, the buffer zone is judged and decided;

[0108] Illustratively, according to the buffer matching degree from high to low, the buffer zone with the largest buffer matching degree is selected to be activated:

[0109] If the buffer matching degree is greater than or equal to 0.7, the first level buffer zone is activated immediately, and the downstream roller speed is adjusted;

[0110] If 0.5 < buffer matching degree < 0.7, the second level buffer zone is started to preheat, such as the temporary storage area in front of the heating furnace;

[0111] If the buffer matching degree is less than or equal to 0.5, the remote scheduling is triggered, such as calling the standby roller;

[0112] It needs to be explained that the buffer matching degree quantifies the adaptive ability of the dynamic buffer zone to the casting blank backlog state; through the ratio of the backlog driving force to the driving force threshold value, the relative severity of the current casting blank queue backlog risk is reflected. The greater the backlog driving force, the more significant the mismatch between the casting blank acceleration and the downstream hot charging furnace speed, and the more intense the backlog trend. This index is directly related to the scheduling pressure that the buffer zone needs to bear;

[0113] Embodiment 2:

[0114] As Figure 1 indicated, a digital-twin-based steelmaking production scheduling method further comprises the following steps:

[0115] S3, a temperature drop model is established for the dynamic buffer zone to obtain a slab temperature drop rate, a theoretical temperature drop amount is obtained by combining a deceleration accumulation trend correction analysis, a temperature after retention is calculated based on the theoretical temperature drop amount, and a hot charging temperature range is compared to determine whether the hot charging demand is met;

[0116] Based on heat transfer theory, a temperature drop rate model is established: The temperature drop rate is obtained ;

[0117] wherein, is a preset comprehensive heat transfer coefficient, which is related to the heat preservation properties of the buffer zone, A / V is a dimensionless ratio of the slab surface area to the volume, reflecting the heat dissipation efficiency, T am is the ambient temperature, and T is the temperature of the slab;

[0118] The theoretical temperature drop amount is obtained by integrating the predicted retention time of the slab in the dynamic buffer zone based on the temperature drop rate;

[0119] wherein, the predicted retention time of the slab is obtained in the following manner:

[0120] If the slab acceleration is less than 0, i.e., the slab queue presents a deceleration accumulation trend, the predicted retention time after trend correction is obtained by the formula: ;

[0121] wherein, respectively, the original predicted retention time of the slab, the current speed, the initial speed, and the acceleration of the slab queue output by the car-following model;

[0122] It can be understood that the original predicted retention time of the slab is obtained by ratio of the processing rate of the dynamic buffer zone and the buffer zone;

[0123] The temperature of the slab after the predicted retention time is calculated based on the theoretical temperature drop amount, and compared with the temperature range in the hot charging stage. If the temperature after the predicted retention time is in the temperature range in the hot charging stage, the hot charging stage demand is met, otherwise it is not met;

[0124] S4, if not met, the slab temperature drop rate is corrected based on the physical field model of heat radiation coupling, the hot charging adaptability is evaluated by dynamic threshold of multi-source data to obtain the hot charging adaptability;

[0125] wherein, the slab temperature drop rate is corrected based on the physical field model of heat radiation coupling in the following manner:

[0126] ​Preferably, the radiation heat flow Qrad between adjacent casting blanks is calculated in combination with the Stefan-Boltzmann law;

[0127] wherein the formula is: the radiation heat flow Qrad between adjacent casting blanks;

[0128] is the emissivity of the casting blank surface (0.8-0.9 for carbon steel), is the Stefan-Boltzmann constant, A is the radiation heat transfer surface area, 、 respectively, the temperature of the adjacent casting blanks ;

[0129] Based on the radiation heat flow Qrad between adjacent casting blanks, the temperature drop rate model is corrected;

[0130] Preferably, the temperature drop rate model is corrected by injecting a radiation correction term: ;

[0131] wherein m is the mass of the casting blank, Cp is the specific heat capacity of the casting blank;

[0132] The hot charging fitness evaluation method based on multi-source data dynamic threshold is:

[0133] Preferably, a threshold generation network model is constructed, the casting blank feature parameter vector is input into the threshold generation network, and a dynamic rate threshold is obtained.

[0134] Wherein the construction method of the casting blank feature parameter vector is:

[0135] The chemical composition, accumulation driving force and safety distance of the casting blank steel grade are normalized respectively to construct the casting blank feature vector.

[0136] The temperature drop consistency coefficient and hot charging temperature compliance rate are obtained, and the temperature drop consistency coefficient and hot charging temperature compliance rate are summed to obtain the hot charging fitness.

[0137] Wherein, the temperature drop consistency coefficient is obtained by formula one: ;

[0138] The temperature compliance rate is obtained by formula two: ;

[0139] Wherein, T is the temperature of the casting blank, T d is the lower limit value of the temperature of the casting blank, and T opt is the target temperature of the hot charging of the casting blank.

[0140] ​​It needs to be explained that the hot charging fitness is a comprehensive index for measuring the matching degree of the temperature state of the continuous casting billet in the hot charging link with the hot charging process requirements. The hot charging fitness is evaluated by quantifying the temperature drop consistency and the temperature compliance rate, so as to assess whether the continuous casting billet is suitable for direct hot charging, and to provide a key basis for production scheduling decision-making.

[0141] The temperature drop consistency coefficient reflects the consistency of the actual temperature drop rate of the continuous casting billet with the expected temperature drop rate. The higher the coefficient, the more stable the temperature drop law of the continuous casting billet in the process of staying or transporting, and the more in line with the requirements of the hot charging process on the temperature retention capability.

[0142] The hot charging temperature compliance rate represents the proportion of the temperature of the continuous casting billet within the allowable temperature range of the hot charging process. The higher the compliance rate, the higher the degree to which the temperature of the continuous casting billet meets the requirements of the hot charging process, and the greater the possibility of directly entering the hot charging link.

[0143] The role of the hot charging fitness is as follows:

[0144] Role one: quantifying the hot charging feasibility to provide dynamic evaluation basis for process decision-making. When the hot charging fitness is greater than or equal to 0.7, it indicates that the temperature drop law of the continuous casting billet is stable and the temperature meets the requirements, so the hot charging process can be directly executed to reduce the additional heating energy consumption. If the fitness is less than 0.5, the system will correct the temperature drop rate based on the Stefan-Boltzmann law and the phase change kinetics equation. For example, for 45# steel in the accumulation state, it is found through the calculation of the radiation heat flow that the actual temperature drop rate is higher than the prediction of the traditional model. After the correction combined with the phase change latent heat effect, the heating power is triggered to increase from 500 kW to 650 kW for compensation, so that the temperature meets the requirements of the hot charging process.

[0145] Role two: driving the space-time constraint scheduling model to optimize the production rhythm matching. The hot charging fitness is the core parameter of the target fusion function minZ. By quantifying the time window degree and the buffer zone tightness, the cutting time and the transportation speed of the continuous casting billet are adjusted in the time dimension to avoid the temperature drop exceeding the standard due to process delay. In the spatial dimension, the buffer zone allocation strategy is optimized to prioritize the continuous casting billet with high hot charging fitness into the furnace. For example, when the buffer zone tightness exceeds the threshold, the system will sort the continuous casting billets according to the hot charging fitness, store the continuous casting billets with low fitness in the secondary buffer zone for preheating, and prioritize the continuous casting billets with high fitness to enter the hot charging furnace. The optimal parameter combination is solved by the genetic algorithm to realize the dynamic matching of the cutting rhythm and the hot charging process.

[0146] S5, build a temperature drop compensation strategy integrating phase change-radiation correction parameters, establish a space-time constraint scheduling model combining the hot charging fitness, and dynamically schedule the continuous casting billet production to optimize the matching of the cutting and hot charging rhythm of the continuous casting billet.

[0147] The way to build a temperature drop compensation strategy integrating phase change-radiation correction parameters is as follows:

[0148] Preferably, the inter-cast blank radiation heat flow is quantified by the Stefan-Boltzmann law, the phase change fraction is calculated in combination with a phase change kinetics equation (such as the MAK equation), the temperature drop rate is corrected, a compensation decision model is established according to the corrected temperature drop parameter, the hot charging temperature threshold and the allowed temperature drop rate, heating power, heating time and residence time adjustment compensation measures are formulated for different temperature drop scenarios, a closed-loop control strategy is formed, and the continuous casting blank temperature drop meets the hot charging process requirements.

[0149] For example, when a steel plant produces 45# steel, the continuous casting blank is in a backlog state, and the traditional model calculates the temperature drop rate as 8℃ / min. Using the radiation correction model, it is found by the Stefan-Boltzmann law that the actual temperature drop rate reaches 10℃ / min due to the small distance between adjacent cast blanks (1.2 times the blank length) and the radiation heat flow;

[0150] At the same time, the cast blank is in the phase change interval of 727℃, and the phase change fraction is calculated as 0.3 according to the JMAK equation, and the latent heat of phase change inhibits the temperature drop, and the rate is corrected to 9℃ / min. The allowed temperature drop rate for this steel grade is 8.5℃ / min, at which time the compensation strategy is automatically started: the heating furnace power is increased from 500kW to 650kW, the heating time is extended by 15 minutes, and the roller conveyor speed is adjusted so that the cast blank stays in the heating zone for 8 minutes longer, realizing the temperature drop rate to meet the hot charging process requirements;

[0151] Among them, the way to establish the space-time constraint scheduling model in combination with the hot charging fitness is:

[0152] A1, quantify the time window degree, establish time constraint control;

[0153] Through the formula: Quantify the time window degree , used to establish time constraint control;

[0154] A2, quantify the buffer zone tension, establish space constraint control;

[0155] Through the formula: Quantify the buffer zone capacity tension , used to establish space constraint control;

[0156] A3, combine time and space constraint control, establish target fusion function;

[0157] Through the formula: Construct the target fusion function minZ;

[0158] Among them, Fit is the hot charging fitness, is the preset proportion coefficient of the fusion function, which is set by the professional technical personnel in the art according to experience;

[0159] Those skilled in the art can understand that the target fusion function is input into the genetic algorithm for solving. The genetic algorithm can search for a parameter combination that makes the target function Z reach the minimum in a complex solution space, and based on the parameter combination, multiple key links in the continuous casting billet production process are dynamically scheduled;

[0160] In the time dimension, the cutting time of the billet and the transportation speed between processes are adjusted according to the calculation results, so that the steelmaking production process meets the hot charging time window requirement, and the time over-window degree is reduced;

[0161] In the space dimension, the storage position and distribution strategy of the billet in the buffer zone are reasonably planned, the charging sequence is optimized according to the feedback of the buffer zone tightness, the billet with high hot charging adaptability is preferentially arranged for hot charging, the hot charging efficiency is improved, and the energy consumption is reduced;

[0162] In the whole production process, the changes of the hot charging adaptability, the time over-window degree and the buffer zone tightness are continuously monitored through real-time monitoring system, and these real-time data are fed back to the scheduling system, so that the scheduling decision is continuously optimized and adjusted. Through this closed-loop control mode, the matching of the billet cutting and hot charging rhythm is realized, which can guarantee the production efficiency and improve the product quality.

[0163] Embodiment 3:

[0164] As shown in FIG. 1, a steelmaking production scheduling system based on digital twinning includes the following modules: Figure 3 Matching identification module: acquire continuous casting billet cutting timing data and roller running parameters, and construct a billet twin through a digital twinning algorithm, dynamically couple analyze the cutting action timing of the billet twin and the roller conveying rate, and judge whether the continuous casting billet cutting optimization and the hot charging rhythm match;

[0165] Buffer establishment module: if not matching, a following model is constructed, and the accumulation driving force is calculated combining the cutting and roller parameters, whether the billet queue motion is in the billet accumulation state is judged based on the accumulation driving force, if it is in the state, a state intensity-space distance fusion model is calculated to establish the buffer matching degree, and the corresponding dynamic buffer zone is activated according to the matching degree sorting;

[0166] Hot charging analysis module: a temperature drop model is established for the dynamic buffer zone to obtain the billet temperature drop rate, the theoretical temperature drop amount is obtained by combining the deceleration accumulation trend correction analysis, the temperature after the lag is calculated based on the theoretical temperature drop amount, and whether it meets the hot charging demand is judged by comparing with the hot charging temperature range;

[0167] Adaptation analysis module: if it does not meet the requirement, the billet temperature drop rate is corrected based on the physical field model of thermal radiation coupling, the hot charging adaptability is evaluated through the multi-source data dynamic threshold, and the hot charging adaptability is obtained;

[0168] Adaptation analysis module: if it does not meet the requirement, the billet temperature drop rate is corrected based on the physical field model of thermal radiation coupling, the hot charging adaptability is evaluated through the multi-source data dynamic threshold, and the hot charging adaptability is obtained;

[0169] Rhythm adjustment module: build a temperature drop compensation strategy that integrates phase transition-radiation correction parameters, establish a space-time constraint scheduling model combined with hot charging fitness, dynamically schedule continuous casting billet production, and optimize the matching of billet cutting and hot charging rhythm.

[0170] Embodiment 4:

[0171] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is run by a processor to realize the steelmaking production scheduling method based on digital twinning.

[0172] In the embodiment, the integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of the above-mentioned method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to a photographing device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal and a software distribution medium. For example, a U disk, a mobile hard disk, a magnetic disk or an optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0173] In the above-mentioned embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0174] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software mode depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0175] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other manners. For example, the apparatus / terminal device embodiments described above are merely schematic; for example, the division of the modules or units is merely logical function division; an actual mapping of physical boundaries can be different, for example, a plurality of units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0176] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0177] The above formulas are dimensionless values calculated, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the most recent real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0178] The basic principles, main features and advantages of the present application are shown and described above. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A digital-twin-based steelmaking production scheduling method, characterized in that: The application relates to a method for dynamically scheduling continuous casting based on a cutting optimization and a hot charging rhythm matching method. The method comprises the following steps: constructing a casting blank twin body through a digital twin algorithm, dynamically coupling cutting action time sequence of the casting blank twin body and a roller conveying rate, and judging whether the cutting optimization of the continuous casting blank and the hot charging rhythm are matched or not; if not matched, a following model is constructed, a backlog driving force is calculated by combining the cutting and roller parameters, whether the movement of the continuous casting blank queue is in a continuous casting blank backlog state is judged based on the backlog driving force, if yes, a state intensity-space distance fusion model is established to calculate a buffer matching degree, and corresponding dynamic buffer zones are activated according to the matching degree; a temperature drop model is established for the dynamic buffer zones to obtain a continuous casting blank temperature drop rate, a theoretical temperature drop amount is obtained by combining a deceleration accumulation trend correction analysis, and whether the hot charging demand is met is judged; if not met, the continuous casting blank temperature drop rate is corrected based on a physical field model of thermal radiation coupling, a hot charging adaptability is evaluated through a multi-source data dynamic threshold, and a hot charging adaptability is obtained; 2. The steelmaking production scheduling method based on digital twinning according to claim 1, characterized in that: a temperature drop compensation strategy is constructed by fusing phase change and radiation correction parameters, a time-space constraint scheduling model is established by combining the hot charging adaptability, and the continuous casting blank production is dynamically scheduled to optimize the cutting optimization and the hot charging rhythm matching. The method for dynamically coupling the cutting action time sequence of the casting blank twin body and the roller conveying rate is as follows: a step signal of a casting blank cutting process ignition time is collected, high-frequency features of the ignition moment are extracted from the step signal, and a cutting action signal is established; a roller rate is obtained and a roller rate curve is constructed, a roller rate curve deceleration inflection point is identified through a differential method, and a roller response signal containing the inflection point time of the roller rate curve is established; signal preprocessing is performed on the cutting action signal and the roller response signal, and a cross-correlation function value of the preprocessed cutting action signal and the roller response signal is obtained; the coupling deviation point of the cutting rate curve and the roller rate curve is determined based on the cross-correlation function value, the two curves are analyzed in shape based on the coupling deviation point, and a shape difference value is obtained; 3. The steelmaking production scheduling method based on digital twinning according to claim 2, characterized in that: the rhythm matching criterion is set based on the shape difference value and the slope response matching degree, and whether the cutting optimization of the continuous casting blank and the hot charging rhythm are matched or not is judged. The method for determining the coupling deviation point is as follows: the index value at the maximum value point of the cross-correlation function value is obtained, and the product is calculated by combining the sampling period, and a coupling time difference is obtained; 4. The steelmaking production scheduling method based on digital twinning according to claim 2, characterized in that: the coupling deviation point is extracted based on the coupling time difference, the coupling deviation point is mapped to the cutting rate curve and the roller rate curve, and the two curves are combined and correspondingly divided into a timely period, a delay period and an abnormal period. The method for obtaining the shape difference value is as follows: the slope response matching degree of the cutting deceleration starting point of the cutting rate curve in the delay period and the roller deceleration inflection point of the roller rate curve is obtained; 5. The steelmaking production scheduling method based on digital twinning according to claim 1, characterized in that: the Frisch distance of the cutting rate curve and the roller rate curve in the delay period is calculated, and a shape difference value is obtained. The method for judging whether the movement of the continuous casting blank queue is in a continuous casting blank backlog state is as follows: a following model is constructed based on a continuous casting blank queue core equation, and a continuous casting blank acceleration is obtained; the continuous casting blank acceleration and the downstream hot charging furnace feeding speed are obtained based on the following model, and a backlog driving force is calculated; 6. The steelmaking production scheduling method based on digital twinning according to claim 1, characterized in that: whether the movement of the continuous casting blank queue is in a continuous casting blank backlog state is judged based on the backlog driving force. The method for performing buffer decision position matching analysis on the continuous casting blank backlog state is as follows: a state intensity-space distance fusion model is constructed, and a buffer matching degree is obtained. Based on the buffer matching degree, the buffer zone is judged and decided.

7. The steelmaking production scheduling method based on digital twinning according to claim 1, characterized in that: The way to obtain the hot charging fitness is: The adjacent billets' radiation heat flow is calculated combined with the Stefan-Boltzmann law; The temperature drop rate model is modified based on the adjacent billets' radiation heat flow; The dynamic rate threshold is obtained by constructing a threshold generation network model and inputting the billet feature parameter vector into the threshold generation network; The temperature drop consistency coefficient is obtained by numerical analysis based on the dynamic rate threshold combined with the temperature drop rate; The hot charging fitness is obtained by summing the temperature drop consistency coefficient and the hot charging temperature compliance rate.

8. The steelmaking production scheduling method based on digital twinning according to claim 1, characterized in that: The way to establish the space-time constraint scheduling model combined with the hot charging fitness is: The time constraint control is established by quantifying the time window degree; The space constraint control is established by quantifying the buffer tension degree; The target fusion function is established combined with the time and space constraint controls.

9. A digital-twin-based steelmaking production scheduling system for implementing the digital-twin-based steelmaking production scheduling method of any one of claims 1-8, characterized in that: The method comprises the following modules: The matching identification module: acquires the continuous casting billet cutting time sequence data and roller running parameters, and constructs a billet twin body through a digital twin algorithm, dynamically couples and analyzes the cutting action time sequence of the billet twin body and the roller conveying rate, and judges whether the continuous casting billet cutting optimization and the hot charging rhythm match; The buffer establishment module: if they do not match, a following model is constructed, the accumulation driving force is calculated combined with the cutting and roller parameters, and it is judged whether the billet queue motion is in the billet accumulation state based on the accumulation driving force, if it is, a state intensity-space distance fusion model is calculated to calculate the buffer matching degree, and the corresponding dynamic buffer zone is activated according to the matching degree sorting; The hot charging analysis module: a temperature drop model is established for the dynamic buffer zone to obtain the billet temperature drop rate, the theoretical temperature drop amount is obtained by correcting and analyzing the deceleration accumulation trend, the temperature after the retention is calculated based on the theoretical temperature drop amount, and it is judged whether the hot charging temperature range meets the hot charging demand; The adaptation analysis module: if it does not meet the demand, the billet temperature drop rate is modified based on the physical field model of the thermal radiation coupling, the hot charging fitness is evaluated through the dynamic threshold of the multi-source data, and the hot charging fitness is obtained; The rhythm adjustment module: a temperature drop compensation strategy is constructed by fusing the phase change-revised parameters of the radiation, a space-time constraint scheduling model is established combined with the hot charging fitness, the continuous casting billet production is dynamically scheduled, and the matching of the billet cutting and the hot charging rhythm is optimized.

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

Images