Sheet metal shape and form synergistic control method and system

Abstract

The present application belongs to the field of metal composite rolling process, and discloses a metal plate shape-property synergic regulation method and system, which comprises the following steps: obtaining target data in the composite rolling process; constructing a shape-property model of the composite plate rolling process based on the target data, wherein the shape-property model comprises a comprehensive performance model and a comprehensive plate shape model; determining the dominant partition of the current rolling state according to the shape-property contribution ratio, and dynamically correcting the comprehensive performance model and the comprehensive plate shape model; based on the corrected comprehensive performance and comprehensive plate shape model, adopting an overall optimization strategy to solve the dynamic weight factors of the comprehensive performance and the comprehensive plate shape, and calculating the comprehensive performance and the comprehensive plate shape; and correcting the roll gap adjustment amount according to the comprehensive performance and the comprehensive plate shape, so as to realize the shape-property synergic regulation of the composite plate. The present application effectively solves the problem that the performance and the plate shape quality are difficult to be synergically controlled in the composite plate rolling process, and significantly improves the control precision and the intelligent level of the composite plate production.

Description

Technical Field

[0001] This invention belongs to the field of metal composite material rolling process, specifically relating to a method and system for synergistic control of the shape and properties of metal sheets. Background Technology

[0002] During the rolling process of metal composite plates, due to the differences in properties between the base material and the cladding material, as well as the complexity of the interface bonding, the deformation evolution of the composite plate exhibits strong dynamic coupling and internal cross-interference. Existing process control methods typically treat shape control and overall performance optimization separately, or rely solely on static models based on ideal independent deformation states, neglecting the dynamic shape-property coupling effect between the base material and the cladding material under actual working conditions. This limitation leads to the distortion of the control model, making it difficult to achieve globally optimal and stable control of the overall quality of the composite plate in actual production. Therefore, there is an urgent need for a new method that can achieve coordinated shape and property control of metal composite plates. Summary of the Invention

[0003] To address the problems existing in the prior art, this invention provides a method and system for coordinated control of the shape properties of metal sheets, realizing the function of coordinated control of the shape properties in metal composite rolling.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] A method for synergistic control of the shape properties of metal sheets, the method comprising:

[0006] S1: Obtain target data during the composite rolling process;

[0007] S2: Based on the target data, construct a shape model of the composite plate rolling process; the comprehensive performance model and the comprehensive plate shape model in the shape model are both composed of a benchmark model and an interactive coupling model. That is, on the basis of representing the benchmark model, an interactive coupling model containing cross-interference terms is introduced to quantify and compensate for the real internal interference, and is obtained by dynamic weight fusion.

[0008] S3: Determine the dominant zone of the current rolling state based on the shape contribution ratio, and dynamically correct the comprehensive performance model and the comprehensive shape model;

[0009] S4: Based on the dynamically modified comprehensive performance model and the dynamically modified comprehensive plate shape model, an overall optimization strategy is adopted to solve the dynamic weight factors of comprehensive performance and comprehensive plate shape, and to calculate the comprehensive performance and comprehensive plate shape.

[0010] S5: Based on the overall performance and the overall plate shape, the roll gap adjustment amount is corrected to achieve coordinated control of the shape and properties of the composite plate.

[0011] Preferably, the comprehensive performance model is as follows:

[0012] ;

[0013] in, For overall performance; As a dynamic weighting factor for overall performance; This serves as the baseline performance model. This is a performance-interactive coupling model;

[0014] ;

[0015] in, For the thickness of the base layer; The overall thickness; The yield strength of the base material; This refers to the coating thickness; The yield strength of the coating material;

[0016] ;

[0017] in, For the interface-coordinated yield strength term; This is a shape-based cross-interference term.

[0018] Preferably, the integrated plate shape model is:

[0019] ;

[0020] in, It is a composite plate shape; For the comprehensive plate shape dynamic weighting factor; As a reference plate shape model; This is a plate-shaped interactive coupling model;

[0021] ;

[0022] in, For the flatness of the base material; The flatness of the coating material;

[0023] ;

[0024] in, For the interface co-straightness term of the material; This refers to the material properties and cross-interference terms.

[0025] Preferably, the method for calculating the shape contribution ratio is as follows:

[0026] ;

[0027] in, Contribution ratio to shape; For target performance; For the target plate shape; This is used to prevent extremely small numbers with a denominator of zero; To prevent the target plate shape from being a very small number of zero.

[0028] Preferably, the intervals include: the plate shape deviation-dominant region, the shape-dynamic coupling region, and the performance deviation-dominant region;

[0029] Among them, the dominant area of ​​plate shape deviation is: ; Shape-based dynamic coupling region: Performance Deviation Dominant Area: ; This is the lower bound threshold for shape coupling. This is the upper bound threshold for shape coupling, and .

[0030] Preferably, the method for dynamically correcting the comprehensive performance model by determining the dominant zone of the current rolling state based on the shape contribution ratio includes:

[0031] ;

[0032] in, The modified material properties interactive coupling model; For the material in the first Dynamic correction factor for collaborative performance under each partition; For the material in the first Dynamic correction factor for shape-related cross-interference terms under each partition; This is the dominant area for plate shape deviation; This is the dynamic coupling region of shape and properties; This is the region dominated by performance deviations.

[0033] Preferably, the method for dynamically correcting the comprehensive shape model by determining the dominant zone of the current rolling state based on the shape contribution ratio includes:

[0034] ;

[0035] in, The modified plate-shaped interactive coupling model of the material; For the material in the first Cooperative plate shape dynamic correction factor under each partition; For the material in the first Dynamic correction factor for cross-interference terms in each partition.

[0036] Preferably, based on the dynamically modified comprehensive performance model and the dynamically modified comprehensive plate shape model, the method for solving the dynamic weight factors of comprehensive performance and comprehensive plate shape using an overall optimization strategy includes:

[0037] Construct the rolling mill bounce equation and rolling force model;

[0038] Based on the mill bounce equation and rolling force model, an objective function is constructed;

[0039] Based on the objective function, overall optimization is performed to solve for the dynamic weighting factors of comprehensive performance and comprehensive plate shape;

[0040] The mill bounce equation is as follows:

[0041] ;

[0042] In the formula, Initial roll gap; For rolling force; This refers to the mill stiffness coefficient. To calculate the thickness;

[0043] The rolling force model is as follows:

[0044] ;

[0045] ;

[0046] ;

[0047] In the formula, For rolling force; For bandwidth; To take into account the horizontal projection length of the contact arc between the roll and the workpiece after flattening; This is the influence coefficient; Resistance to metal deformation; The coefficient representing the influence of pre- and post-tension stress on rolling force; This is the reference influence coefficient when there is no plate shape deviation; This is the plate shape correction factor; This is a performance correction factor;

[0048] The objective function is:

[0049] ;

[0050] In the formula, This is the measured rolling force; For the calculated rolling force; The actual thickness; For the calculated thickness; and The coefficient used to balance the weights of the two biases; The vectors represent the dynamic weighting factors for overall performance and the dynamic weighting factors for overall plate shape.

[0051] Based on the objective function, methods for overall optimization and solving for the dynamic weighting factors of comprehensive performance and comprehensive plate shape include:

[0052] Initialize parameters: Use gradient descent to set the initial starting point for optimization. Objective function convergence tolerance Solution vector stability tolerance Maximum number of iterations and learning rate Differential step size ;

[0053] Entering the iteration loop includes the following steps:

[0054] For the The next iteration, with the current solution Based on;

[0055] The objective function is calculated using the numerical difference method. In the present gradient vector at :

[0056] ;

[0057] in, For the objective function in The gradient vector at that point; This is the partial derivative of the objective function with respect to the dynamic weighting factor of the overall performance; Let be the partial derivative of the objective function with respect to the dynamic weighting factor of the overall plate shape. For the first The comprehensive weight factor solution vector at the next iteration;

[0058] Update the estimated value of the solution vector:

[0059] ;

[0060] in, The updated solution vector;

[0061] Perform a convergence check and output the current optimal solution.

[0062] Preferably, the method for adjusting the roll gap amount based on the overall performance and the overall plate shape to achieve synergistic control of the shape and properties of the composite plate includes:

[0063] ;

[0064] In the formula, This refers to the roller gap adjustment amount; This is a correction factor; It is the equivalent plasticity coefficient; For performance weighting coefficients; This refers to the plate shape weighting coefficient; Performance-roll gap influence coefficient; The influence coefficient of plate shape and roll gap; The target thickness.

[0065] The present invention also provides a metal sheet shape and property coordinated control system, the system being used to implement the aforementioned method, the system comprising: an acquisition module, a construction module, a correction module, a solution module, and an adjustment module;

[0066] The acquisition module is used to acquire target data during the composite rolling process;

[0067] The construction module is used to construct a shape model of the composite plate rolling process based on the target data. The comprehensive performance model and the comprehensive plate shape model in the shape model are both composed of a benchmark model and an interactive coupling model. That is, on the basis of the characterizing benchmark model, an interactive coupling model containing cross-interference terms is introduced to quantify and compensate for the real internal interference, and is obtained by dynamic weight fusion.

[0068] The correction module is used to determine the dominant partition based on the shape contribution ratio and to dynamically correct the comprehensive performance model and the comprehensive plate shape model.

[0069] The solution module is used to solve for the dynamic weight factors of comprehensive performance and comprehensive shape based on the dynamically modified comprehensive performance model and the dynamically modified comprehensive shape model, using an overall optimization strategy, and to calculate the comprehensive performance and comprehensive shape.

[0070] The adjustment module is used to correct the roll gap adjustment amount based on the overall performance and the overall plate shape, so as to achieve coordinated control of the shape and properties of the composite plate.

[0071] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0072] This invention constructs a composite rolling morphology collaborative model that includes a baseline model and interactive coupling terms. It effectively solves the problem that the deformation state of multilayer metal materials is difficult to quantify accurately due to interface cross-interference in real rolling, and provides a reliable underlying basis for significantly improving the quality of composite plate products.

[0073] This invention innovatively introduces the shape contribution ratio for partition diagnosis, realizing dynamic adaptive correction of interference terms in the performance interaction coupling model and the plate shape interaction coupling model, overcoming the defect of traditional fixed parameter models being prone to distortion under complex working conditions.

[0074] This invention employs an overall optimization algorithm, which effectively overcomes the blindness of traditional trial-and-error methods based on experience, and ensures that the solved comprehensive performance and the dynamic weight factor of the comprehensive plate shape have high accuracy.

[0075] This invention possesses intelligent decision-making capabilities based on shape-dominant zoning. It can automatically match the corresponding zoning correction coefficient according to the current real-time status and adjust the roll gap accordingly, thereby achieving high-precision coordination and intelligent control of the composite board production process. Attached Figure Description

[0076] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the 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.

[0077] Figure 1 This is an overall flowchart of a method for synergistic control of the shape and properties of metal sheets according to an embodiment of the present invention;

[0078] Figure 2 This is a flowchart illustrating an embodiment of the present invention;

[0079] Figure 3 This is an overall optimization flowchart of an embodiment of the present invention. Detailed Implementation

[0080] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0081] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0082] Example 1

[0083] like Figures 1-3 As shown, this embodiment discloses a method for synergistic control of the shape and properties of metal sheets, including the following steps:

[0084] S1: Obtain target data during the composite rolling process.

[0085] S2: Based on the target data, construct a shape-property model of the composite plate rolling process. To address the problem that existing models neglect interlayer interference, the comprehensive performance model and comprehensive plate shape model in the shape-property model are both composed of a baseline model and an interactive coupling model. That is, based on the baseline model representing ideal independent deformation, an interactive coupling model containing cross-interference terms is introduced to quantify and compensate for the actual internal interference, and the result is obtained through dynamic weight fusion.

[0086] S3: Determine the dominant zone of the current rolling state based on the shape contribution ratio, and dynamically correct the comprehensive performance model and comprehensive shape model.

[0087] S4: Based on the dynamically corrected comprehensive performance and the dynamically corrected comprehensive plate shape model, an overall optimization strategy is adopted to solve the dynamic weight factors of comprehensive performance and comprehensive plate shape, and to calculate the comprehensive performance and comprehensive plate shape.

[0088] S5: Based on the overall performance and overall shape, the roll gap adjustment amount is corrected to achieve synergistic control of the shape and properties of the composite board.

[0089] In this embodiment of the invention, the target data in S1 includes the base coat thickness, target performance expectation value, target shape expectation value, target thickness, reduction amount, and material properties. The specific acquisition process for the above data is as follows: setting parameters such as target performance, shape expectation value, and target thickness are set according to actual needs; real-time status data such as base coat thickness and reduction amount are acquired in real time through online sensors on the rolling mill; and material performance data is obtained by calling the basic material physical property database.

[0090] In this embodiment of the invention, the comprehensive performance model and the comprehensive plate shape model in S2 take yield strength and straightness as examples, respectively. The model construction includes the following sub-steps:

[0091] S21: Baseline performance model construction;

[0092] S22: Construction of a performance interaction coupling model;

[0093] S23: Based on the benchmark performance model and the performance interaction coupling model, complete the construction of the comprehensive performance model;

[0094] S24: Construction of the baseline plate shape model;

[0095] S25: Construction of Plate-Shaped Interactive Coupling Model;

[0096] S26: Based on the baseline plate shape model and the plate shape interaction coupling model, complete the construction of the comprehensive plate shape model.

[0097] S21 Reference performance model This represents the sum of the yield strengths of the base and overburden layers under ideal, independent deformation conditions excluding interfacial interference. The formula for calculating this sum is:

[0098] ;

[0099] in, For the thickness of the base layer; The overall thickness; The yield strength of the base material; This refers to the coating thickness; is the yield strength of the coating material.

[0100] The relationship between the overall thickness of the composite panel and the thickness of the base layer and the cladding layer is as follows:

[0101] ;

[0102] S22 Performance Inter-coupling Model This indicates that in the actual rolling of composite plates, due to the presence of interfaces, the evolution of shape will produce complex internal interference, the calculation formula of which is:

[0103] ;

[0104] in, This is a performance-interactive coupling model; For the interface-coordinated yield strength term; This is a shape-based cross-interference term.

[0105] The comprehensive performance model described in S23 This is represented by a dynamic weighting factor for overall performance, based on the aforementioned benchmark and interference compensation term. The degree of interference can be controlled, and the calculation formula is as follows:

[0106] ;

[0107] in, For overall performance; This is a dynamic weighting factor for overall performance.

[0108] S24 Reference plate shape model This represents the benchmark for the straightness variation of the base and overburden layers under ideal, independent deformation conditions excluding interfacial interference. Its calculation formula is:

[0109] ;

[0110] in, As a reference plate shape model; For the flatness of the base material; The flatness of the coating material.

[0111] S25 Plate-shaped interactive coupling model This indicates that in the actual rolling of composite plates, due to the presence of interfaces, the evolution of shape will produce complex internal interference, the calculation formula of which is:

[0112] ;

[0113] in, This is a plate-shaped interactive coupling model; For the interface co-straightness term of the material; This refers to the material properties and cross-interference terms.

[0114] S26 Comprehensive plate shape model This is represented by a comprehensive plate shape dynamic weighting factor introduced based on the aforementioned benchmark and interference compensation term. The degree of interference can be controlled, and the calculation formula is as follows:

[0115] ;

[0116] in, It is a composite plate shape; This is a comprehensive dynamic weighting factor for the plate shape.

[0117] In this embodiment of the invention, S3 includes the following sub-steps:

[0118] S31: Construction of the shape contribution score region;

[0119] S32: Dynamic correction of the performance interaction coupling model and the plate shape interaction coupling model.

[0120] The shape contribution ratio in S31 The calculation formula is:

[0121] ;

[0122] in, Contribution ratio to shape; For target performance; For the target plate shape; This is used to prevent extremely small numbers with a denominator of zero; To prevent the target plate shape from being a very small number of zero.

[0123] The specific partitions are as follows:

[0124] Plate shape deviation dominant area ( At this point, the relative deviation of the plate shape is much greater than the performance;

[0125] Shape-based dynamic coupling region ( The performance is comparable to the degree of deviation from the plate shape;

[0126] Performance Deviation Dominant Region ( At this point, the relative deviation of performance becomes dominant;

[0127] in, This is the lower bound threshold for shape coupling. This is the upper bound threshold for shape coupling, and The aforementioned thresholds can be calibrated based on the material properties of the target composite plate and historical rolling test data.

[0128] Based on the shape contribution ratio in S32 The interval in which the performance interaction coupling model is located. Dynamic adjustments are made to obtain the corrected performance interaction coupling model. The details are as follows:

[0129] ;

[0130] in, The modified material properties interactive coupling model; For the material in the first Dynamic correction factor for collaborative performance under each partition; For the material in the first Dynamic correction factor for shape-related cross-interference terms under each partition; This is the dominant area for plate shape deviation; This is the dynamic coupling region of shape and properties; This is the region dominated by performance deviations.

[0131] Plate-shaped interactive coupling model Dynamic corrections are performed to obtain the corrected plate-shaped interactive coupling model. The details are as follows:

[0132] ;

[0133] in, The modified plate-shaped interactive coupling model of the material; For the material in the first Cooperative plate shape dynamic correction factor under each partition; For the material in the first Dynamic correction factor for cross-interference terms in each partition.

[0134] Synergistic performance dynamic correction factor Dynamic correction factor for shape-related cross-interference terms With the collaborative plate shape dynamic correction factor Dynamic correction factor for cross-interference terms The correction strategy varies depending on the state of the dominant partition:

[0135] In the region dominated by plate shape deviation, given the large plate shape error, a dynamic correction factor for synergistic performance is introduced. With the collaborative plate shape dynamic correction factor The interface collaboration performance and interface collaboration board shape are modified, and a dynamic correction factor for the shape cross-interference term is introduced. Dynamic correction factor for cross-interference terms with shape Correct the shape-shape cross-interference term and the property-shape cross-interference term;

[0136] In the dynamic coupling region of form and property, since the performance is comparable to the plate shape error, a collaborative performance dynamic correction factor is introduced. With the collaborative plate shape dynamic correction factor The interface collaboration performance and interface collaboration board shape are modified, and a dynamic correction factor for the shape cross-interference term is introduced. Dynamic correction factor for cross-interference terms with shape Correct the shape-shape cross-interference term and the property-shape cross-interference term;

[0137] In the region dominated by performance deviation, given the large performance deviation, a collaborative performance dynamic correction factor is introduced. With the collaborative plate shape dynamic correction factor The interface collaboration performance and interface collaboration board shape are modified, and a dynamic correction factor for the shape cross-interference term is introduced. Dynamic correction factor for cross-interference terms with shape The shape-shape cross-interference term and the property-shape cross-interference term are modified.

[0138] In this embodiment of the invention, S4 includes the following sub-steps:

[0139] S41: Construction of rolling mill bounce equation and rolling force model;

[0140] S42: Based on the mill bounce equation and rolling force model, construct the objective function and define the optimization problem;

[0141] S43: Overall optimization.

[0142] The mill bounce equation described in S41 is:

[0143] ;

[0144] In the formula, Initial roll gap; For rolling force; This refers to the mill stiffness coefficient. To calculate the thickness.

[0145] The rolling force model is as follows:

[0146] ;

[0147] ;

[0148] ;

[0149] In the formula, For rolling force; For bandwidth; To take into account the horizontal projection length of the contact arc between the roll and the workpiece after flattening; This is the influence coefficient; Resistance to metal deformation; The coefficient representing the influence of pre- and post-tension stress on rolling force; This is the reference influence coefficient when there is no plate shape deviation; This is the plate shape correction factor; This is a performance correction factor.

[0150] The optimization problem defined in S42 is:

[0151] Define the dynamic weighting factor for overall performance and the dynamic weighting factor for overall plate shape as follows: ;

[0152] The objective function The core is to measure the deviation between the model's calculated values ​​and the actual measured values. The model is constructed as follows:

[0153] ;

[0154] In the formula, This is the measured rolling force; For the calculated rolling force; The actual thickness; For the calculated thickness; and The coefficient is used to balance the weights of the two biases.

[0155] The overall optimization described in S43 includes the following sub-steps:

[0156] S431: Initialization parameters;

[0157] S432: Iterative loop;

[0158] S431 uses the gradient descent method. An initial starting point for optimization is set. Objective function convergence tolerance Solution vector stability tolerance Maximum number of iterations and learning rate Differential step size .

[0159] S432 enters the iteration loop, including the following steps:

[0160] (1) For the first The next iteration, with the current solution Based on;

[0161] (2) The objective function is calculated using the numerical difference method. In the present gradient vector at ;

[0162] ;

[0163] ;

[0164] in, This is the partial derivative of the objective function with respect to the dynamic weighting factor of the overall performance; This is the partial derivative of the objective function with respect to the dynamic weighting factor of the overall plate shape; For the first The comprehensive weight factor solution vector at the next iteration; For the first Estimated dynamic weighting factors for overall performance at the next iteration; For the first Estimated value of the dynamic weight factor of the integrated plate shape at the next iteration.

[0165] Constructing gradient vectors for:

[0166] ;

[0167] in, For the objective function in The gradient vector at that point.

[0168] (3) Update the estimated value of the solution vector:

[0169] ;

[0170] in, This is the updated solution vector.

[0171] (4) There are two methods to determine convergence:

[0172] Method 1: The current solution has made the objective function sufficiently small, and the objective function has converged.

[0173] ;

[0174] Method 2: The iterative solution has essentially stopped changing, and the solution vector is stable.

[0175] ;

[0176] If any of the above conditions are met, the iteration terminates, and the final dynamic weight factor solution is output:

[0177] ;

[0178] Otherwise, proceed to the next step:

[0179] ;

[0180] Return to step (1) and continue iterating until the maximum number of iterations is reached. Force termination and output the current optimal solution.

[0181] Subsequently, the optimal comprehensive performance dynamic weighting factor obtained by the solution will be... With the optimal comprehensive plate shape dynamic weight factor Substitute them into the aforementioned comprehensive performance model respectively With integrated plate shape model In this way, the final comprehensive performance after dynamic collaborative correction is calculated. With comprehensive plate shape .

[0182] Specifically, in this embodiment, S5 zoning control involves the system dividing the system into zones based on the comprehensive performance and comprehensive shape contribution ratio obtained in S4, and selecting different weighting coefficients to adjust the roll gap. The specific calculation formula for the roll gap adjustment amount is as follows:

[0183] ;

[0184] In the formula, This refers to the roller gap adjustment amount; This is a correction factor; It is the equivalent plasticity coefficient; For performance weighting coefficients; This refers to the plate shape weighting coefficient; Performance-roll gap influence coefficient; The influence coefficient of plate shape and roll gap; The target thickness.

[0185] Performance - Roll Gap Influence Coefficient With the influence coefficient of plate shape and roll gap It was obtained by regression fitting calibration of historical rolling data.

[0186] In addition to ensuring that the overall export thickness meets the target, it is also necessary to meet the requirements of various performance characteristics and plate shape. Therefore, a performance weighting coefficient is introduced. and plate shape weight coefficient The roll gap adjustment is corrected. Both coefficients are dimensionless parameters, and their values ​​are obtained by fitting historical data. The correction method varies depending on the morphological contribution ratio zone:

[0187] In the region dominated by plate shape deviation, a performance weighting coefficient is introduced. and plate shape weight coefficient The correction is made because the relative deviation of the plate shape is much greater than the performance at this time. The control system needs to prioritize the flatness of the composite plate, and the urgency of plate shape adjustment is more sensitive. Therefore, the performance weight coefficient is less than the plate shape weight coefficient.

[0188] In the form-dynamic coupling region, a performance weighting coefficient is introduced. and plate shape weight coefficient The correction is made because the deviation between performance and shape is similar, and the two are in a state of strong dynamic coupling and synergy. The control requirements are equally important, so the difference between the performance weight coefficient and the shape weight coefficient is small.

[0189] In the region dominated by performance deviation, a performance weighting coefficient is introduced. and plate shape weight coefficient Corrections are made because the relative deviation of performance dominates at this point, and the control system needs to prioritize compensating for the deviation of yield strength. The urgency of performance adjustment is more sensitive, so the performance weight coefficient is greater than the plate shape weight coefficient.

[0190] Example 2

[0191] The present invention also provides a metal sheet shape and property coordinated control system, the system being used to implement the method described in Embodiment 1, the system comprising: an acquisition module, a construction module, a correction module, a solution module, and an adjustment module;

[0192] The acquisition module is used to acquire target data during the composite rolling process;

[0193] The construction module is used to construct a shape model of the composite plate rolling process based on the target data. The comprehensive performance model and the comprehensive plate shape model in the shape model are both composed of a benchmark model and an interactive coupling model. That is, on the basis of the characterizing benchmark model, an interactive coupling model containing cross-interference terms is introduced to quantify and compensate for the real internal interference, and is obtained by dynamic weight fusion.

[0194] The correction module is used to determine the dominant partition based on the shape contribution ratio and to dynamically correct the comprehensive performance model and the comprehensive plate shape model.

[0195] The solution module is used to solve for the dynamic weight factors of the comprehensive performance and the comprehensive shape based on the dynamically modified comprehensive performance model and the dynamically modified comprehensive shape model, and to calculate the comprehensive performance and comprehensive shape by adopting an overall optimization strategy.

[0196] The adjustment module is used to correct the roll gap adjustment amount based on the overall performance and the overall plate shape, so as to achieve coordinated control of the shape and properties of the composite plate.

[0197] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for synergistic control of the shape and properties of metal sheets, characterized in that, The method includes: S1: Obtain target data during the composite rolling process; target data includes base coat thickness, target performance expectation value, target plate shape expectation value, target thickness, as well as reduction amount and material properties; S2: Based on the target data, construct a shape model of the composite plate rolling process; the comprehensive performance model and the comprehensive plate shape model in the shape model are both composed of a benchmark model and an interactive coupling model. That is, on the basis of representing the benchmark model, an interactive coupling model containing cross-interference terms is introduced to quantify and compensate for the real internal interference, and is obtained by dynamic weight fusion. The comprehensive performance model is as follows: ； in, For overall performance; As a dynamic weighting factor for overall performance; This serves as the baseline performance model. This is a performance-interactive coupling model; ； in, For the thickness of the base layer; The overall thickness; The yield strength of the base material; This refers to the coating thickness; The yield strength of the coating material; ； in, For the interface-coordinated yield strength term; These are shape-related cross-interference terms; The comprehensive plate shape model is as follows: ； in, It is a composite plate shape; For the comprehensive plate shape dynamic weighting factor; As a reference plate shape model; This is a plate-shaped interactive coupling model; ； in, For the flatness of the base material; The flatness of the coating material; ； in, For the interface co-straightness term of the material; For material properties and cross-interference terms; S3: Determine the dominant zone of the current rolling state based on the shape contribution ratio, and dynamically correct the comprehensive performance model and the comprehensive shape model; S4: Based on the dynamically modified comprehensive performance model and the dynamically modified comprehensive plate shape model, an overall optimization strategy is adopted to solve the dynamic weight factors of comprehensive performance and comprehensive plate shape, and to calculate the comprehensive performance and comprehensive plate shape. S5: Based on the overall performance and the overall plate shape, the roll gap adjustment amount is corrected to achieve synergistic control of the shape and properties of the composite plate.

2. The method according to claim 1, characterized in that, The method for calculating the shape contribution ratio is as follows: ； in, Contribution ratio to shape; For target performance; For the target plate shape; This is used to prevent extremely small numbers with a denominator of zero; To prevent the target plate shape from being a very small number of zero.

3. The method according to claim 2, characterized in that, The intervals include: the plate shape deviation-dominant region, the shape-property dynamic coupling region, and the performance deviation-dominant region; Among them, the dominant area of ​​plate shape deviation is: ; Shape-based dynamic coupling region: Performance Deviation Dominant Area: ; This is the lower bound threshold for shape coupling. This is the upper bound threshold for shape coupling, and .

4. The method according to claim 3, characterized in that, The method for dynamically correcting the comprehensive performance model by determining the dominant zone of the current rolling state based on the shape contribution ratio includes: ； in, The modified material properties interactive coupling model; For the material in the first Dynamic correction factor for collaborative performance under each partition; For the material in the first Dynamic correction factor for shape-related cross-interference terms under each partition; This is the dominant area for plate shape deviation; This is the dynamic coupling region of shape and properties; This is the region dominated by performance deviations.

5. The method according to claim 4, characterized in that, The method for dynamically correcting the comprehensive plate shape model by determining the dominant zone of the current rolling state based on the shape contribution ratio includes: ； in, The modified plate-shaped interactive coupling model of the material; For the material in the first Cooperative plate shape dynamic correction factor under each partition; For the material in the first Dynamic correction factor for cross-interference terms in each partition.

6. The method according to claim 5, characterized in that, Based on the dynamically modified comprehensive performance model and the dynamically modified comprehensive plate shape model, the method for solving the dynamic weight factors of comprehensive performance and comprehensive plate shape using an overall optimization strategy includes: Construct the rolling mill bounce equation and rolling force model; Based on the mill bounce equation and rolling force model, an objective function is constructed; Based on the objective function, overall optimization is performed to solve for the dynamic weighting factors of comprehensive performance and comprehensive plate shape; The mill bounce equation is as follows: ； In the formula, Initial roll gap; For rolling force; This refers to the mill stiffness coefficient. To calculate the thickness; The rolling force model is as follows: ； ； ； In the formula, For rolling force; For bandwidth; To take into account the horizontal projection length of the contact arc between the roll and the workpiece after flattening; This is the influence coefficient; Resistance to metal deformation; The coefficient representing the influence of pre- and post-tension stress on rolling force; This is the reference influence coefficient when there is no plate shape deviation; This is the plate shape correction factor; This is a performance correction factor; The objective function is: ； In the formula, This is the measured rolling force; For the calculated rolling force; The actual thickness; For the calculated thickness; and The coefficient used to balance the weights of the two biases; The vectors represent the dynamic weighting factors for overall performance and the dynamic weighting factors for overall plate shape. Based on the objective function, methods for overall optimization and solving for the dynamic weighting factors of comprehensive performance and comprehensive plate shape include: Initialize parameters: Use gradient descent to set the initial starting point for optimization. Objective function convergence tolerance Solution vector stability tolerance Maximum number of iterations and learning rate Differential step size ; Entering the iteration loop includes the following steps: For the The next iteration, with the current solution Based on; The objective function is calculated using the numerical difference method. In the present gradient vector at : ； in, For the objective function in The gradient vector at that point; This is the partial derivative of the objective function with respect to the dynamic weighting factor of the overall performance; Let be the partial derivative of the objective function with respect to the dynamic weighting factor of the overall plate shape. For the first The comprehensive weight factor solution vector at the next iteration; Update the estimated value of the solution vector: ； in, The updated solution vector; Perform a convergence check and output the current optimal solution.

7. The method according to claim 6, characterized in that, Based on the overall performance and the overall plate shape, the method for adjusting the roll gap amount to achieve synergistic control of the shape and properties of the composite plate includes: ； In the formula, This refers to the roller gap adjustment amount; This is a correction factor; It is the equivalent plasticity coefficient; For performance weighting coefficients; This refers to the plate shape weighting coefficient; Performance-roll gap influence coefficient; The influence coefficient of plate shape and roll gap; The target thickness.

8. A metal sheet shape and property coordinated control system, said system being used to implement the method described in any one of claims 1-7, characterized in that, The system includes: an acquisition module, a construction module, a correction module, a solution module, and an adjustment module; The acquisition module is used to acquire target data during the composite rolling process; the target data includes base coat thickness, target performance expectation value, target plate shape expectation value, target thickness, as well as reduction amount and material properties; The construction module is used to construct a shape model of the composite plate rolling process based on the target data. The comprehensive performance model and the comprehensive plate shape model in the shape model are both composed of a benchmark model and an interactive coupling model. That is, on the basis of the characterizing benchmark model, an interactive coupling model containing cross-interference terms is introduced to quantify and compensate for the real internal interference, and is obtained by dynamic weight fusion. The comprehensive performance model is as follows: ； in, For overall performance; As a dynamic weighting factor for overall performance; This serves as the baseline performance model. This is a performance-interactive coupling model; ； in, For the thickness of the base layer; The overall thickness; The yield strength of the base material; This refers to the coating thickness; The yield strength of the coating material; ； in, For the interface-coordinated yield strength term; These are shape-related cross-interference terms; The comprehensive plate shape model is as follows: ； in, It is a composite plate shape; For the comprehensive plate shape dynamic weighting factor; As a reference plate shape model; This is a plate-shaped interactive coupling model; ； in, For the flatness of the base material; The flatness of the coating material; ； in, For the interface co-straightness term of the material; For material properties and cross-interference terms; The correction module is used to determine the dominant partition based on the shape contribution ratio and to dynamically correct the comprehensive performance model and the comprehensive plate shape model. The solution module is used to solve for the dynamic weight factors of comprehensive performance and comprehensive shape based on the dynamically modified comprehensive performance model and the dynamically modified comprehensive shape model, using an overall optimization strategy, and to calculate the comprehensive performance and comprehensive shape. The adjustment module is used to correct the roll gap adjustment amount based on the overall performance and the overall plate shape, so as to achieve coordinated control of the shape and properties of the composite plate.

Images