A hot continuous rolling rhythm dynamic monitoring method and device based on digital twinning

Abstract

This invention relates to the field of digital twin systems, and specifically to a method and apparatus for dynamic monitoring of hot strip rolling rhythm based on digital twins. The method includes: using digital twin technology to simulate production; obtaining the time-varying curves of the head and tail positions of the rolled piece through a spatiotemporal prediction model of the rolled piece's motion; dividing the time-varying curves of the head and tail positions of the rolled piece based on the equipment sections of the production line; inputting actual production data; calculating the optimized tapping time interval using a dynamic optimization model of hot strip rolling rhythm based on predicted tapping time interval, predicted transportation time, predicted processing time, and actual production data; and dynamically adjusting the rolling rhythm of the hot strip rolling production line according to the optimized tapping time interval. This invention provides a highly efficient dynamic monitoring method for rolling rhythm based on digital twins for the hot strip rolling production process.

Description

Technical Field

[0001] This invention relates to the field of digital twin system technology, and in particular to a method and device for dynamic monitoring of hot continuous rolling rhythm based on digital twin. Background Technology

[0002] Research on improving the production efficiency and energy consumption of hot-rolled strip steel has always been a hot topic in the steel industry. Among them, rolling rhythm control directly affects the production efficiency and energy consumption of hot-rolled strip production lines. Rolling rhythm control, under the constraints of equipment, process, and automation control, optimizes the waiting time of raw material slabs entering the production line in order to minimize the product production interval.

[0003] By increasing the rolling rhythm, production waiting time can be shortened, the pure processing rate of equipment can be improved, production capacity can be increased, and energy consumption can be reduced. In existing hot-rolled strip steel production, due to the high-temperature environment of the production line, the production line cannot be organically integrated with monitoring equipment, resulting in a low degree of automation in the autonomous control of the rolling rhythm. In continuous production, it is not possible to effectively achieve dynamic optimization of the rolling rhythm.

[0004] In the existing technology, there is a lack of an efficient dynamic monitoring method for rolling rhythm based on digital twins for hot continuous rolling production processes. Summary of the Invention

[0005] This invention provides a method and apparatus for dynamic monitoring of hot strip rolling rhythm based on digital twins. The technical solution is as follows:

[0006] On the one hand, a method for dynamic monitoring of hot strip rolling rhythm based on digital twin is provided. This method is implemented by electronic equipment and includes:

[0007] A production line model is constructed using digital twin technology to obtain a dynamic monitoring model of the rolling rhythm; production simulation is performed based on the dynamic monitoring model of the rolling rhythm to obtain simulated production data;

[0008] Based on the simulated production data, the time-varying curves of the head and tail positions of the rolled piece are obtained through the spatiotemporal prediction model of the rolled piece motion.

[0009] Based on the equipment sections of the production line, the curves showing the change of the head and tail positions of the rolled piece over time are divided to obtain the predicted transportation time and predicted processing time for each equipment section.

[0010] The predicted steel tapping time interval is obtained by calculating based on the curve of the head and tail positions of the rolled piece changing over time.

[0011] Input actual production data, and calculate the optimized steel tapping time interval based on the predicted steel tapping time interval, the predicted transportation time, the predicted processing time, and the actual production data using the hot strip rolling rhythm dynamic optimization model.

[0012] Based on the optimized steel tapping time interval, the rolling rhythm of the hot continuous rolling production line is dynamically adjusted.

[0013] The rolling rhythm dynamic monitoring model includes: a production line physical space model, a production line virtual space model, a production process monitoring model, and an industrial data transmission monitoring model.

[0014] Optionally, obtaining the time-varying curves of the head and tail positions of the rolled piece using a spatiotemporal prediction model based on the simulated production data includes:

[0015] Based on the simulated production data, the production speed setting data is obtained;

[0016] Based on the production speed setting data, the rolling mill motion prediction curve is obtained through the rolling mill motion spatiotemporal prediction model; the rolling mill motion spatiotemporal prediction model is a mathematical prediction model based on the process characteristics of the production line.

[0017] The curves showing the change of the head and tail positions of the rolled piece over time are obtained by calculating based on the preset head and tail parameters of the rolled piece and the predicted movement curve of the rolled piece.

[0018] Optionally, the input of actual production data, based on the predicted tapping time interval, the predicted transportation time, the predicted processing time, and the actual production data, is used to calculate the optimized tapping time interval through a dynamic optimization model of hot strip rolling rhythm, including:

[0019] The actual transportation time and actual processing time are calculated based on the actual production data.

[0020] The transportation time adjustment time is calculated based on the actual transportation time and the predicted transportation time.

[0021] The processing time adjustment time is calculated based on the actual processing time and the predicted processing time.

[0022] The production adjustment time is calculated based on the transportation time adjustment time and the processing time adjustment time.

[0023] The optimized steel tapping time is obtained based on the predicted steel tapping time interval and the production adjustment time.

[0024] Optionally, after obtaining the optimized tapping time interval, the method further includes:

[0025] The actual steel tapping time interval is obtained based on the actual production time.

[0026] Based on the actual steel tapping time interval and the optimized steel tapping time interval, the predicted adjustment amount for steel tapping time is obtained;

[0027] Based on the predicted adjustment amount of the tapping time, the prediction adjustment parameters are obtained through the tapping prediction self-learning model; the tapping prediction self-learning model is used to optimize the tapping time prediction for the next batch based on the predicted adjustment amount of the current batch.

[0028] The spatiotemporal prediction model for the movement of the rolled piece is optimized based on the prediction adjustment parameters.

[0029] On the other hand, a digital twin-based hot strip rolling rhythm dynamic monitoring device is provided. This device is applied to a digital twin-based hot strip rolling rhythm dynamic monitoring method. The device includes:

[0030] The production simulation module is used to construct a production line model using digital twin technology to obtain a dynamic monitoring model of the rolling rhythm; and to perform production simulation based on the dynamic monitoring model of the rolling rhythm to obtain simulated production data.

[0031] The roll head and tail curve acquisition module is used to obtain the roll head and tail position change curves over time based on the simulated production data and the roll motion spatiotemporal prediction model.

[0032] The equipment segment time acquisition module is used to divide the curve of the change of the head and tail position of the rolled piece over time based on the equipment segment of the production line, and obtain the predicted transportation time and predicted processing time of each equipment segment.

[0033] The predicted steel tapping interval calculation module is used to calculate the predicted steel tapping interval based on the curve of the head and tail positions of the rolled piece changing over time.

[0034] The steel tapping interval optimization module is used to input actual production data and calculate the optimized steel tapping interval based on the predicted steel tapping interval, the predicted transportation time, the predicted processing time, and the actual production data through the hot strip rolling rhythm dynamic optimization model.

[0035] The rolling rhythm adjustment module is used to dynamically adjust the rolling rhythm of the hot continuous rolling production line according to the optimized steel tapping time interval.

[0036] The rolling rhythm dynamic monitoring model includes: a production line physical space model, a production line virtual space model, a production process monitoring model, and an industrial data transmission monitoring model.

[0037] Optionally, the roll head and tail curve acquisition module is further used for:

[0038] Based on the simulated production data, the production speed setting data is obtained;

[0039] Based on the production speed setting data, the rolling mill motion prediction curve is obtained through the rolling mill motion spatiotemporal prediction model; the rolling mill motion spatiotemporal prediction model is a mathematical prediction model based on the process characteristics of the production line.

[0040] The curves showing the change of the head and tail positions of the rolled piece over time are obtained by calculating based on the preset head and tail parameters of the rolled piece and the predicted movement curve of the rolled piece.

[0041] Optionally, the steel tapping interval optimization module is further used for:

[0042] The actual transportation time and actual processing time are calculated based on the actual production data.

[0043] The transportation time adjustment time is calculated based on the actual transportation time and the predicted transportation time.

[0044] The processing time adjustment time is calculated based on the actual processing time and the predicted processing time.

[0045] The production adjustment time is calculated based on the transportation time adjustment time and the processing time adjustment time.

[0046] The optimized steel tapping time is obtained based on the predicted steel tapping time interval and the production adjustment time.

[0047] Optionally, the steel tapping interval optimization module is further used for:

[0048] The actual steel tapping time interval is obtained based on the actual production time.

[0049] Based on the actual steel tapping time interval and the optimized steel tapping time interval, the predicted adjustment amount for steel tapping time is obtained;

[0050] Based on the predicted adjustment amount of the tapping time, the prediction adjustment parameters are obtained through the tapping prediction self-learning model; the tapping prediction self-learning model is used to optimize the tapping time prediction for the next batch based on the predicted adjustment amount of the current batch.

[0051] The spatiotemporal prediction model for the movement of the rolled piece is optimized based on the prediction adjustment parameters.

[0052] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above-mentioned method for dynamic monitoring of hot strip rolling rhythm based on digital twin.

[0053] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the above-described method for dynamic monitoring of hot strip rolling rhythm based on digital twin.

[0054] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0055] This invention provides a method for dynamic monitoring of hot strip rolling rhythm based on digital twins. By utilizing digital twin technology, a digital twin system for dynamic monitoring of rolling rhythm is constructed, enabling real-time tracking and monitoring during production. Through analysis of the spatial layout and actions of production equipment, as well as the process flow, and combined with production process data, spatiotemporal prediction of the movement of rolled pieces during hot strip rolling is achieved. Based on this, a dynamic optimization model for hot strip rolling rhythm is designed. By defining the "transport time" and "processing time" of each segment, the steel tapping time interval of the rolled piece is calculated, achieving dynamic monitoring and optimization of the rolling rhythm. A self-learning function for steel tapping prediction is introduced to continuously improve optimization accuracy. This invention establishes a real-time tracking model and a real-time state optimization method for hot strip rolling. Through a three-dimensional virtual model, real-time tracking and mapping of the strip steel is achieved, and the tapping time of the next rolled piece can be dynamically adjusted based on real-time data. This provides valuable reference and guidance for on-site operators in managing and controlling the rolling rhythm of hot strip rolling. This invention is a highly efficient dynamic monitoring method for rolling rhythm based on digital twins for hot strip rolling production processes. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart of a method for dynamic monitoring of hot strip rolling rhythm based on digital twin provided in an embodiment of the present invention;

[0058] Figure 2 This is a schematic diagram of a hot continuous rolling production line layout provided in an embodiment of the present invention;

[0059] Figure 3 This is a block diagram of a hot continuous rolling mill rolling rhythm dynamic monitoring device based on digital twin provided in an embodiment of the present invention;

[0060] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0061] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0062] This invention provides a method for dynamic monitoring of hot strip rolling rhythm based on digital twins. This method can be implemented by electronic devices, such as terminals or servers. Figure 1 The flowchart shown is a method for dynamic monitoring of hot strip rolling rhythm based on digital twins. The processing flow of this method may include the following steps:

[0063] S1. Use digital twin technology to build a production line model and obtain a dynamic monitoring model of rolling rhythm; conduct production simulation based on the dynamic monitoring model of rolling rhythm to obtain simulated production data.

[0064] The rolling rhythm dynamic monitoring model includes: production line physical space model, production line virtual space model, production process monitoring model, and industrial data transmission monitoring model.

[0065] In one feasible implementation, a hot strip rolling production line is the actual application scenario of this invention. After the steel exits the heating furnace, the slab sequentially undergoes rough descaling (HSB), side-press width setting (SSP), roughing mill No. 1 (R1), roughing mill No. 2 (R2), flying shear (Crop Shear, CS), fine descaling (FSB), finish rolling (F1~F7), laminar cooling (LC), and coiler coiling. The roughing process of this production line is divided into two types: "3+3" and "3+5", that is, three passes and five passes when rolling the slab in R2, corresponding to the production of thick and thin strip steel, respectively.

[0066] Based on digital twin technology, a digital twin system for dynamic monitoring of rolling rhythm was constructed, such as... Figure 2 As shown, the specific expression is as shown in equation (1):

[0067] M DT ={PS,VS,M&C,DD,CN} (1)

[0068] In this model, PS represents the physical space model of the production line; VS represents the virtual space model of the production line; M&C represents the production process monitoring model; DD represents stored data; and CN represents the data transmission monitoring model based on the Industrial Internet.

[0069] The digital twin of a hot strip mill production line includes a mapping path and a feedback path. The main functions of the mapping path are physical information collection and dynamic behavior mapping; physical information acquisition primarily includes various signals throughout the process lifecycle. The feedback path configures decision data into the physical system (PS). In the dynamic system (VS), process decisions are collected after data analysis. The manufacturing and control (M&C) system can also deploy configuration data in the physical space to control parameters within the process.

[0070] S2. Based on the simulated production data, the time-varying curves of the head and tail positions of the rolled piece are obtained through the spatiotemporal prediction model of the rolled piece motion.

[0071] Optionally, based on simulated production data, the time-varying curves of the head and tail positions of the rolled piece are obtained using a spatiotemporal prediction model of the rolled piece's motion, including:

[0072] Based on the simulated production data, the production speed setting data is obtained;

[0073] Based on the production speed setting data, the rolling mill motion prediction curve is obtained through the rolling mill motion spatiotemporal prediction model; the rolling mill motion spatiotemporal prediction model is a mathematical prediction model based on the process characteristics of the production line.

[0074] The curves showing the change of the head and tail positions of the rolled piece over time are obtained by calculating based on the preset head and tail parameters and the predicted movement curve of the rolled piece.

[0075] In one feasible implementation, spatiotemporal prediction utilizes the hot strip rolling process parameters in the data to calculate the positions of the head and tail of the strip about to exit the rolling mill at each moment, obtaining a curve showing the change of the head and tail positions over time. By predicting the positions of the head and tail of the strip throughout the entire production process, the relative relationship between the strip length and its position at each moment can be observed. Spatiotemporal prediction is primarily based on the speed setting data of fully automated hot strip rolling production. By integrating the speed and combining it with the process characteristics at various points on the production line, the final spatiotemporal prediction curve for hot strip rolling is obtained.

[0076] When the workpiece moves on the roller table, the speed of the workpiece is the same as the speed of the roller table, and the position p of the workpiece head. head and the tail position p of the rolled piece tail Calculate the following equations (2) and (3):

[0077] P head =vt (2)

[0078] P tail =vt-l slab (3)

[0079] Where v is the roller speed; t is the time elapsed for the rolled piece; I slab This refers to the length of the rolled piece.

[0080] When the workpiece is rolled, the slab deforms, and the relative positions of its head and tail change. The position p of the workpiece head changes. head and the tail position p of the rolled piece tail Calculate the following equations (3) and (4):

[0081] P head =v out t (3)

[0082] P tail =v in tl slab (4)

[0083] Among them, the head speed of the rolled piece v out and the tail speed v of the rolled piece in Calculate the following equations (5) and (6):

[0084] v out =(1+SFR)v wrspd (5)

[0085] v in =(1-SBR)v wrspd (6)

[0086] Where SFR is the forward slip value; SBR is the backward slip value; v wrspd This refers to the rolling speed.

[0087] S3. Based on the equipment sections of the production line, the curves showing the change of the head and tail positions of the rolled piece over time are divided to obtain the predicted transportation time and predicted processing time for each equipment section.

[0088] In one feasible implementation, the present invention adopts the actual hot strip mill production line equipment segment division, as shown in Table 1 (2250 Hot Strip Mill Production Line Segmentation Table):

[0089] Table 1

[0090]

[0091] The rolling stock passes through each segment sequentially, and the actual start time (ST) of the rolling stock in each machine segment is calculated using actual data values. j，i Completion time CT j，i The calculation formulas are shown in equations (7), (8), (9), (10), and (11) below:

[0092] ST j+1，1 =CT j，m (7)

[0093] ST j+1，i ≥CT j，i +a i (8)

[0094] r j，1 =0 (9)

[0095]

[0096]

[0097] Where m is the total number of machines; a i Preparation time for machine segment i; p j，i The processing time of rolled piece j in section i of machine; r j，i Let be the transport time of rolled piece j from machine segment i-1 to machine segment i.

[0098] A typical production plan involves producing dozens of coils of strip steel. However, in this invention, the calculation of the steel output interval for the next slab only requires the actual production information of the previous slab. Therefore, the calculation is performed by selecting the first three slabs that enter production from the actual production plan.

[0099] Based on the calculations of production time and space prediction, the transportation time and processing time of each production line segment, as well as the arrival time and completion time of the slab in each processing segment, are obtained. The results of the rolling rhythm prediction are summarized as shown in Table 2 (H210389090 segment time calculation table) and Table 3 (H210389100 segment time calculation table):

[0100] Table 2

[0101] Transportation time (s) 0 5.801 19.142 10.422 2.915 18.792 -66.959 -55.656 Processing time (s) 12.036 61.849 41.934 12.679 53.757 80.743 81.392 70.655 Start time (s) 0 17.837 98.828 151.184 166.778 239.327 253.111 278.847 Completion time (s) 12.036 79.686 140.762 163.863 220.535 320.07 334.503 349.502

[0102] Table 3

[0103] Transportation time (s) 0 5.801 19.142 10.422 2.915 18.792 -69.439 -53.765 Processing time (s) 12.036 62.172 45.032 13.047 55.823 81.317 85.382 73.795 Start time (s) 0 17.837 99.151 154.605 170.567 245.182 257.06 288.677 Completion time (s) 12.036 80.009 144.183 167.652 226.39 326.499 342.442 362.472

[0104] S4. Calculate the predicted steel tapping time interval based on the curve of the head and tail positions of the rolled piece changing with time.

[0105] In one feasible implementation, the time interval between the exits of two adjacent rolled pieces is calculated based on the completion time of the preceding rolled piece and the start time of the following rolled piece. The ideal interval between rolled pieces j and j+1 in machine segment i is also considered. The calculation formula is shown in equation (12) below:

[0106]

[0107] Based on the interval time of each segment, the time interval D between the tapping of two adjacent rolled pieces j and j+1 is... j,j+1 The calculation formula is shown in equation (13) below:

[0108]

[0109] The results of the rolling rhythm predictions were summarized, and the overlap time was calculated based on Tables 2 and 3. This overlap time was then added to the set minimum interval time to obtain the countdown for the next rolled piece in each segment. As shown in Table 4 (Prediction Table of Steel Tap-out Time for H210389100), the maximum value was taken, and the preliminary predicted steel tap-out time for slab H210389100 was 92.443 seconds.

[0110] Table 4

[0111] Overlap time 12.036 61.849 41.611 9.258 49.968 74.888 77.443 60.825 R1 interval - - 15 - - - - - R2 interval - - - - 15 - - - FM interval - - - - - - 15 - DC interval - - - - - - - 0 Next countdown 12.036 61.849 56.611 9.258 64.968 74.888 92.443 60.825

[0112] S5. Input actual production data, and calculate the optimized steel tapping time interval based on the predicted steel tapping time interval, predicted transportation time, predicted processing time and actual production data through the dynamic optimization model of hot continuous rolling rhythm.

[0113] Optionally, actual production data is input, and the optimized steel tapping time interval is obtained by calculating using a dynamic optimization model of hot strip rolling rhythm based on the predicted steel tapping time interval, predicted transportation time, predicted processing time, and actual production data. This includes:

[0114] The actual transportation time and actual processing time are calculated based on actual production data.

[0115] The transportation time adjustment time is calculated based on the actual transportation time and the predicted transportation time.

[0116] The processing time adjustment time is calculated based on the actual processing time and the predicted processing time.

[0117] The production adjustment time is calculated based on the adjustment time for transportation time and the adjustment time for processing time.

[0118] The optimal tapping time is obtained based on the predicted tapping time interval and production adjustment time.

[0119] In one feasible implementation, after the rolled steel is actually tapped, the deviations between the actual and calculated values ​​of the transportation and processing times for each segment are compared in real time, and the tapping time interval is dynamically adjusted.

[0120] In actual production, the impact of numerical disturbances is taken into account. Based on real-time tracking data of the rolled piece, the difference Δr between the actual and calculated transportation time is calculated. j，i And the difference Δp between the actual and calculated processing time. j，i The calculation formulas for transportation time adjustment time and processing time adjustment time are shown in the following formula (14):

[0121]

[0122] Where, r′ j，ip′ represents the actual transport time of rolled piece j from machine section i-1 to machine section i; j，i The actual processing time of rolled piece j in section i of machine.

[0123] The sum of two differences The calculation of the dynamic production adjustment time for the rolling rhythm is shown in the following formula (15):

[0124]

[0125] The data sampling frequency at the production site can typically reach the millisecond level, which ensures the real-time optimization of steel tapping time.

[0126] After slab H210389090 begins processing, it is tracked and monitored. Here, we take the slab passing through the rough descaling section as an example. After obtaining the actual speed data of the slab in the rough descaling transport section, the actual motion curve for that section can be calculated. By observing a local portion of the curve, it can be found that there is a certain deviation between the actual processing process and the predicted result. The deviation adjustment ΔT1 corresponding to the magnified part on the time axis is 0.054 seconds, indicating that there is a fluctuation between the actual value and the set value of the process parameters, causing the actual processing curve to deviate. It is necessary to adjust the subsequent prediction time, advancing the corresponding ΔT1 time. The updated results of the tapping time prediction are shown in Table 5 (H210389090 segmented time update table) and Table 6 (H210389100 tapping time prediction update table):

[0127] Table 5

[0128] Transportation time (s) 0 5.801 19.142 10.422 2.915 18.792 -66.959 -55.656 Processing time (s) 11.982 61.849 41.934 12.679 53.757 80.743 81.392 70.655 Start time (s) 0 17.783 98.774 151.13 166.724 239.273 253.057 278.793 Completion time (s) 11.982 79.632 140.708 163.809 220.481 320.016 334.449 349.448

[0129] Table 6

[0130] Overlap time 11.982 61.795 41.557 9.204 49.914 74.834 77.389 60.771 R1 interval - - 15 - - - - - R2 interval - - - - 15 - - - FM interval - - - - - - 15 - DC interval - - - - - - - 0 Next countdown 12.036 61.849 56.557 9.258 64.914 74.888 92.389 60.825

[0131] Optionally, after obtaining the optimized tapping time interval, the method further includes:

[0132] The actual steel tapping time interval is obtained based on the actual production time.

[0133] Based on the actual steel tapping time interval and the optimized steel tapping time interval, the predicted adjustment amount for steel tapping time is obtained;

[0134] Based on the adjustment amount of the steel tapping time prediction, the prediction adjustment parameters are obtained through the steel tapping prediction self-learning model; the steel tapping prediction self-learning model is used to optimize the steel tapping time prediction for the next batch based on the adjustment amount of the current batch prediction.

[0135] The spatiotemporal prediction model for the movement of the rolled piece is optimized based on the prediction adjustment parameters.

[0136] In one feasible implementation, the present invention uses the difference between the actual value and the calculated value of the tapping time interval to determine the adjustment amount of the tapping time interval of subsequent rolled pieces, thereby optimizing the tapping time prediction results.

[0137] The prediction of the rolling process does not take into account the lifting and lowering speeds of the lifting roller conveyor, resulting in an error between the predicted and actual tapping time of the rolled piece that has already exited the heating furnace. The formula for calculating the adjustment amount of the predicted tapping time is as follows (16):

[0138] ΔT=T pre_disc -T real_disc (16)

[0139] Where ΔT is the adjustment amount for the tapping time of the already tapped slab; T pre_disc This is the predicted value for the countdown to steel production; T real_disc This is the measured value for the countdown to steel production.

[0140] For the same batch of rolling plans, the rolling process curve and rolling rhythm are regular. The adjustment amount of the rolling piece to be rolled can be determined by using the adjustment amount ΔT of the rolling time of the already rolled slab. Therefore, a self-learning model for rolling prediction is established based on ΔT. The mathematical expression of the self-learning model for rolling prediction is shown in the following equation (17):

[0141] ΔT i+1 =ΔT i α+ΔT i-1 (1-α) (17)

[0142] Where, ΔT i+1 The adjustment amount for the tapping time of the (i+1)th rolled piece; ΔT i and ΔT i-1 These are the adjustment amounts for the i-th and i-1-th rolled pieces that have already been produced; α is the self-learning adjustment coefficient, which is usually taken between 0.6 and 0.8.

[0143] S6. Dynamically adjust the rolling rhythm of the hot continuous rolling production line according to the optimized steel tapping time interval.

[0144] In one feasible implementation, the result of the dynamic adjustment of the tapping time according to the present invention is compared with the original tapping rhythm setting on site, as shown in Table 7 (Comparison Table of Rolling Rhythm Monitoring Effect). The on-site rolling rhythm control mode is automatic tapping mode, and the tapping time interval varies for a batch of plans. To ensure safe production, the system selects the longest time interval as the fixed tapping interval, and in the batch of plans selected for the experiment, the automatic tapping time interval is 120 seconds. As can be seen from the comparison in the table, the hot rolling tapping time after dynamic adjustment is shortened by nearly 30 seconds, resulting in higher efficiency. The result after tapping time prediction self-learning adjustment differs from the actual result by within 50ms, which can meet the accuracy requirements of on-site tapping time control.

[0145] Table 7

[0146]

[0147]

[0148] This invention provides a method for dynamic monitoring of hot strip rolling rhythm based on digital twins. By utilizing digital twin technology, a digital twin system for dynamic monitoring of rolling rhythm is constructed, enabling real-time tracking and monitoring during production. Through analysis of the spatial layout and actions of production equipment, as well as the process flow, and combined with production process data, spatiotemporal prediction of the movement of rolled pieces during hot strip rolling is achieved. Based on this, a dynamic optimization model for hot strip rolling rhythm is designed. By defining the "transport time" and "processing time" of each segment, the steel tapping time interval of the rolled piece is calculated, achieving dynamic monitoring and optimization of the rolling rhythm. A self-learning function for steel tapping prediction is introduced to continuously improve optimization accuracy. This invention establishes a real-time tracking model and a real-time state optimization method for hot strip rolling. Through a three-dimensional virtual model, real-time tracking and mapping of the strip steel is achieved, and the tapping time of the next rolled piece can be dynamically adjusted based on real-time data. This provides valuable reference and guidance for on-site operators in managing and controlling the rolling rhythm of hot strip rolling. This invention is a highly efficient dynamic monitoring method for rolling rhythm based on digital twins for hot strip rolling production processes.

[0149] Figure 3 This is a block diagram illustrating a dynamic monitoring device for hot strip rolling rhythm based on digital twins, according to an exemplary embodiment. (Refer to...) Figure 3 The device includes:

[0150] The production simulation module 310 is used to construct a production line model using digital twin technology to obtain a dynamic monitoring model of the rolling rhythm; and to perform production simulation based on the dynamic monitoring model of the rolling rhythm to obtain simulated production data.

[0151] The head and tail curve acquisition module 320 is used to obtain the head and tail position change curves of the rolled piece over time based on the simulated production data and the spatiotemporal prediction model of the rolled piece motion.

[0152] The equipment segment time acquisition module 330 is used to divide the curve of the change of the head and tail position of the rolled piece over time based on the equipment segment of the production line, and obtain the predicted transportation time and predicted processing time of each equipment segment.

[0153] The steel tapping interval calculation module 340 is used to calculate the predicted steel tapping interval based on the curve of the head and tail positions of the rolled piece changing over time.

[0154] The steel tapping interval optimization module 350 is used to input actual production data. Based on the predicted steel tapping interval, predicted transportation time, predicted processing time and actual production data, it calculates the optimized steel tapping interval through the hot continuous rolling rhythm dynamic optimization model.

[0155] The rolling rhythm adjustment module 360 ​​is used to dynamically adjust the rolling rhythm of the hot strip rolling production line according to the optimized steel tapping time interval.

[0156] The rolling rhythm dynamic monitoring model includes: production line physical space model, production line virtual space model, production process monitoring model, and industrial data transmission monitoring model.

[0157] Optionally, the roll head and tail curve acquisition module 320 is further used for:

[0158] Based on the simulated production data, the production speed setting data is obtained;

[0159] Based on the production speed setting data, the rolling mill motion prediction curve is obtained through the rolling mill motion spatiotemporal prediction model; the rolling mill motion spatiotemporal prediction model is a mathematical prediction model based on the process characteristics of the production line.

[0160] The curves showing the change of the head and tail positions of the rolled piece over time are obtained by calculating based on the preset head and tail parameters and the predicted movement curve of the rolled piece.

[0161] Optionally, the steel tapping interval optimization module 350 is further used for:

[0162] The actual transportation time and actual processing time are calculated based on actual production data.

[0163] The transportation time adjustment time is calculated based on the actual transportation time and the predicted transportation time.

[0164] The processing time adjustment time is calculated based on the actual processing time and the predicted processing time.

[0165] The production adjustment time is calculated based on the adjustment time for transportation time and the adjustment time for processing time.

[0166] The optimal tapping time is obtained based on the predicted tapping time interval and production adjustment time.

[0167] Optionally, the steel tapping interval optimization module 350 is also used for:

[0168] The actual steel tapping time interval is obtained based on the actual production time.

[0169] Based on the actual steel tapping time interval and the optimized steel tapping time interval, the predicted adjustment amount for steel tapping time is obtained;

[0170] Based on the adjustment amount of the steel tapping time prediction, the prediction adjustment parameters are obtained through the steel tapping prediction self-learning model; the steel tapping prediction self-learning model is used to optimize the steel tapping time prediction for the next batch based on the adjustment amount of the current batch prediction.

[0171] The spatiotemporal prediction model for the movement of the rolled piece is optimized based on the prediction adjustment parameters.

[0172] This invention provides a method for dynamic monitoring of hot strip rolling rhythm based on digital twins. By utilizing digital twin technology, a digital twin system for dynamic monitoring of rolling rhythm is constructed, enabling real-time tracking and monitoring during production. Through analysis of the spatial layout and actions of production equipment, as well as the process flow, and combined with production process data, spatiotemporal prediction of the movement of rolled pieces during hot strip rolling is achieved. Based on this, a dynamic optimization model for hot strip rolling rhythm is designed. By defining the "transport time" and "processing time" of each segment, the steel tapping time interval of the rolled piece is calculated, achieving dynamic monitoring and optimization of the rolling rhythm. A self-learning function for steel tapping prediction is introduced to continuously improve optimization accuracy. This invention establishes a real-time tracking model and a real-time state optimization method for hot strip rolling. Through a three-dimensional virtual model, real-time tracking and mapping of the strip steel is achieved, and the tapping time of the next rolled piece can be dynamically adjusted based on real-time data. This provides valuable reference and guidance for on-site operators in managing and controlling the rolling rhythm of hot strip rolling. This invention is a highly efficient dynamic monitoring method for rolling rhythm based on digital twins for hot strip rolling production processes.

[0173] Figure 4This is a schematic diagram of the structure of an electronic device 400 provided in an embodiment of the present invention. The electronic device 400 may vary considerably due to different configurations or performance. It may include one or more central processing units (CPUs) 401 and one or more memories 402. The memory 402 stores at least one instruction, which is loaded and executed by the processor 401 to implement the steps of the above-mentioned dynamic monitoring method for hot continuous rolling rhythm based on digital twin.

[0174] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including instructions that can be executed by a processor in a terminal to complete the aforementioned method for dynamic monitoring of hot strip rolling rhythm based on digital twins. For example, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0175] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0176] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for dynamic monitoring of hot continuous rolling rhythm based on digital twin, characterized in that, The method includes: A production line model is constructed using digital twin technology to obtain a dynamic monitoring model of the rolling rhythm; production simulation is performed based on the dynamic monitoring model of the rolling rhythm to obtain simulated production data; Based on the simulated production data, the time-varying curves of the head and tail positions of the rolled piece are obtained through a spatiotemporal prediction model of the rolled piece motion, including: Based on the simulated production data, the production speed setting data is obtained; Based on the production speed setting data, the rolling mill motion prediction curve is obtained through the rolling mill motion spatiotemporal prediction model; the rolling mill motion spatiotemporal prediction model is a mathematical prediction model based on the process characteristics of the production line. The curves showing the change of the head and tail positions of the rolled piece over time are obtained by calculating based on the preset head and tail parameters of the rolled piece and the predicted motion curve of the rolled piece. Based on the equipment sections of the production line, the curves showing the change of the head and tail positions of the rolled piece over time are divided to obtain the predicted transportation time and predicted processing time for each equipment section. The predicted steel tapping time interval is obtained by calculating based on the curve of the head and tail positions of the rolled piece changing over time. Inputting actual production data, and based on the predicted steel tapping time interval, the predicted transportation time, the predicted processing time, and the actual production data, the optimized steel tapping time interval is calculated using a dynamic optimization model for hot strip rolling rhythm, including: The actual transportation time and actual processing time are calculated based on the actual production data. The transportation time adjustment time is calculated based on the actual transportation time and the predicted transportation time. The processing time adjustment time is calculated based on the actual processing time and the predicted processing time. The production adjustment time is calculated based on the transportation time adjustment time and the processing time adjustment time. Based on the predicted steel tapping time interval and the production adjustment time, an optimized steel tapping time interval is obtained; After obtaining the optimized steel tapping time interval, the method further includes: The actual steel tapping time interval is obtained based on the actual production time. Based on the actual steel tapping time interval and the optimized steel tapping time interval, the predicted adjustment amount for steel tapping time is obtained; Based on the predicted adjustment amount of the tapping time, the prediction adjustment parameters are obtained through the tapping prediction self-learning model; the tapping prediction self-learning model is used to optimize the tapping time prediction for the next batch based on the predicted adjustment amount of the current batch. The spatiotemporal prediction model for the movement of the rolled piece is optimized based on the prediction adjustment parameters. Based on the optimized steel tapping time interval, the rolling rhythm of the hot continuous rolling production line is dynamically adjusted.

2. The method for dynamic monitoring of hot continuous rolling rhythm based on digital twin as described in claim 1, characterized in that, The rolling rhythm dynamic monitoring model includes: a production line physical space model, a production line virtual space model, a production process monitoring model, and an industrial data transmission monitoring model.

3. A dynamic monitoring device for hot continuous rolling rhythm based on digital twin, characterized in that, The device includes: The production simulation module is used to construct a production line model using digital twin technology to obtain a dynamic monitoring model of the rolling rhythm; and to perform production simulation based on the dynamic monitoring model of the rolling rhythm to obtain simulated production data. The roll head and tail curve acquisition module is used to obtain the roll head and tail position change curves over time based on the simulated production data and the roll motion spatiotemporal prediction model. The module for obtaining the head and tail curves of the rolled piece is used for: Based on the simulated production data, the production speed setting data is obtained; Based on the production speed setting data, the rolling mill motion prediction curve is obtained through the rolling mill motion spatiotemporal prediction model; the rolling mill motion spatiotemporal prediction model is a mathematical prediction model based on the process characteristics of the production line. The curves showing the change of the head and tail positions of the rolled piece over time are obtained by calculating based on the preset head and tail parameters of the rolled piece and the predicted motion curve of the rolled piece. The equipment segment time acquisition module is used to divide the curve of the change of the head and tail position of the rolled piece over time based on the equipment segment of the production line, and obtain the predicted transportation time and predicted processing time of each equipment segment. The predicted steel tapping interval calculation module is used to calculate the predicted steel tapping interval based on the curve of the head and tail positions of the rolled piece changing over time. The steel tapping interval optimization module is used to input actual production data and calculate the optimized steel tapping interval based on the predicted steel tapping interval, the predicted transportation time, the predicted processing time, and the actual production data through the hot strip rolling rhythm dynamic optimization model. The steel tapping interval optimization module is used for: The actual transportation time and actual processing time are calculated based on the actual production data. The transportation time adjustment time is calculated based on the actual transportation time and the predicted transportation time. The processing time adjustment time is calculated based on the actual processing time and the predicted processing time. The production adjustment time is calculated based on the transportation time adjustment time and the processing time adjustment time. Based on the predicted steel tapping time interval and the production adjustment time, an optimized steel tapping time interval is obtained; The steel tapping interval optimization module is further used for: The actual steel tapping time interval is obtained based on the actual production time. Based on the actual steel tapping time interval and the optimized steel tapping time interval, the predicted adjustment amount for steel tapping time is obtained; Based on the predicted adjustment amount of the tapping time, the prediction adjustment parameters are obtained through the tapping prediction self-learning model; the tapping prediction self-learning model is used to optimize the tapping time prediction for the next batch based on the predicted adjustment amount of the current batch. The spatiotemporal prediction model for the movement of the rolled piece is optimized based on the prediction adjustment parameters. The rolling rhythm adjustment module is used to dynamically adjust the rolling rhythm of the hot continuous rolling production line according to the optimized steel tapping time interval.

4. The hot continuous rolling rhythm dynamic monitoring device based on digital twin according to claim 3, characterized in that, The rolling rhythm dynamic monitoring model includes: a production line physical space model, a production line virtual space model, a production process monitoring model, and an industrial data transmission monitoring model.

Images